def get_gain_bias(ens, rng=np.random):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = ens.neuron_type.max_rates_intercepts(
gain, bias)
if (ens.max_rates is not Ensemble.max_rates.default or
ens.intercepts is not Ensemble.intercepts.default):
warnings.warn(NengoWarning(
"Specifying the gains and biases for %s imposes a set of "
"maximum firing rates and intercepts. Further specifying "
"either max_rates or intercepts has no effect." % ens))
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (
not np.all(np.isfinite(gain)) or np.any(gain <= 0.)):
raise BuildError(
"The specified intercepts for %s lead to neurons with "
"negative or non-finite gain. Please adjust the intercepts so "
"that all gains are positive. For most neuron types (e.g., "
"LIF neurons) this is achieved by reducing the maximum "
"intercept value to below 1." % ens)
return gain, bias, max_rates, intercepts
def get_gain_bias(ens, rng=np.random):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = ens.neuron_type.max_rates_intercepts(
gain, bias)
if (ens.max_rates is not Ensemble.max_rates.default
or ens.intercepts is not Ensemble.intercepts.default):
warnings.warn(NengoWarning(
"Specifying the gains and biases for %s imposes a set of "
"maximum firing rates and intercepts. Further specifying "
"either max_rates or intercepts has no effect." % ens))
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (
not np.all(np.isfinite(gain)) or np.any(gain <= 0.)):
raise BuildError(
"The specified intercepts for %s lead to neurons with "
"negative or non-finite gain. Please adjust the intercepts so "
"that all gains are positive. For most neuron types (e.g., "
"LIF neurons) this is achieved by reducing the maximum "
"intercept value to below 1." % ens)
return gain, bias, max_rates, intercepts
def get_gain_bias(ens, rng=np.random, intercept_limit=1.0, dtype=None):
# Modified from the Nengo version to handle `intercept_limit`
dtype = nengo.rc.float_dtype if dtype is None else dtype
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = ens.neuron_type.max_rates_intercepts(gain, bias)
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError(
"gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens
)
else:
int_distorarray = ens.intercepts
if isinstance(int_distorarray, nengo.dists.Uniform):
if int_distorarray.high > intercept_limit:
warnings.warn(
"Intercepts are larger than intercept limit (%g). "
"High intercept values cause issues when discretizing "
"the model for running on Loihi." % intercept_limit
)
int_distorarray = nengo.dists.Uniform(
min(int_distorarray.low, intercept_limit),
min(int_distorarray.high, intercept_limit),
)
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(int_distorarray, ens.n_neurons, rng=rng)
if np.any(intercepts > intercept_limit):
intercepts[intercepts > intercept_limit] = intercept_limit
warnings.warn(
"Intercepts are larger than intercept limit (%g). "
"High intercept values cause issues when discretizing "
"the model for running on Loihi." % intercept_limit
)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (not np.all(np.isfinite(gain)) or np.any(gain <= 0.0)):
raise BuildError(
f"{ens}: The specified intercepts lead to neurons with negative or "
"non-finite gain. Please adjust the intercepts so that all gains are "
"positive. For most neuron types (e.g., LIF neurons) this is achieved "
"by reducing the maximum intercept value to below 1."
)
dtype = nengo.rc.float_dtype
gain = gain.astype(dtype) if gain is not None else gain
bias = bias.astype(dtype) if bias is not None else bias
max_rates = max_rates.astype(dtype) if max_rates is not None else max_rates
intercepts = intercepts.astype(dtype) if intercepts is not None else intercepts
return gain, bias, max_rates, intercepts
def get_gain_bias(ens, rng=np.random):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = None, None # TODO: determine from gain & bias
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
return gain, bias, max_rates, intercepts
def get_gain_bias(ens, rng=np.random):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = None, None # TODO: determine from gain & bias
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
return gain, bias, max_rates, intercepts
def get_gain_bias(ens, rng=np.random, dtype=None):
"""Compute concrete gain and bias for ensemble."""
dtype = rc.float_dtype if dtype is None else dtype
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = ens.neuron_type.max_rates_intercepts(gain, bias)
if (
ens.max_rates != Ensemble.max_rates.default
or ens.intercepts != Ensemble.intercepts.default
):
warnings.warn(
NengoWarning(
f"Specifying the gains and biases for {ens} imposes a set of "
"maximum firing rates and intercepts. Further specifying "
"either max_rates or intercepts has no effect."
)
)
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError(
f"gain or bias set for {ens}, but not both. "
"Solving for one given the other is not implemented yet."
)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (not np.all(np.isfinite(gain)) or np.any(gain <= 0.0)):
raise BuildError(
f"The specified intercepts for {ens} lead to neurons with "
"negative or non-finite gain. Please adjust the intercepts so "
"that all gains are positive. For most neuron types (e.g., "
"LIF neurons) this is achieved by reducing the maximum "
"intercept value to below 1."
)
gain = gain.astype(dtype) if gain is not None else gain
bias = bias.astype(dtype) if bias is not None else bias
max_rates = max_rates.astype(dtype) if max_rates is not None else max_rates
intercepts = intercepts.astype(dtype) if intercepts is not None else intercepts
return gain, bias, max_rates, intercepts
def make_state(self, n_neurons, rng=np.random, dtype=None):
dtype = rc.float_dtype if dtype is None else dtype
state = {}
initial_state = {} if self.initial_state is None else self.initial_state
for name in self.state:
dist = initial_state.get(name, self.state[name])
state[name] = get_samples(dist, n=n_neurons, d=None,
rng=rng).astype(dtype, copy=False)
return state
def get_gain_bias(ens, rng=np.random, intercept_limit=1.0):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = ens.neuron_type.max_rates_intercepts(
gain, bias)
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
int_distorarray = ens.intercepts
if isinstance(int_distorarray, nengo.dists.Uniform):
if int_distorarray.high > intercept_limit:
warnings.warn(
"Intercepts are larger than intercept limit (%g). "
"High intercept values cause issues when discretizing "
"the model for running on Loihi." % intercept_limit)
int_distorarray = nengo.dists.Uniform(
min(int_distorarray.low, intercept_limit),
min(int_distorarray.high, intercept_limit))
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(int_distorarray, ens.n_neurons, rng=rng)
if np.any(intercepts > intercept_limit):
intercepts[intercepts > intercept_limit] = intercept_limit
warnings.warn(
"Intercepts are larger than intercept limit (%g). "
"High intercept values cause issues when discretizing "
"the model for running on Loihi." % intercept_limit)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (
not np.all(np.isfinite(gain)) or np.any(gain <= 0.)):
raise BuildError(
"The specified intercepts for %s lead to neurons with "
"negative or non-finite gain. Please adjust the intercepts so "
"that all gains are positive. For most neuron types (e.g., "
"LIF neurons) this is achieved by reducing the maximum "
"intercept value to below 1." % ens)
return gain, bias, max_rates, intercepts
def build_ensemble(model, ens):
# Create random number generator
rng = np.random.RandomState(model.seeds[ens])
eval_points = gen_eval_points(ens, ens.eval_points, rng=rng)
# Set up encoders
if isinstance(ens.neuron_type, nengo.Direct):
encoders = np.identity(ens.dimensions)
elif isinstance(ens.encoders, Distribution):
encoders = get_samples(ens.encoders,
ens.n_neurons,
ens.dimensions,
rng=rng)
else:
encoders = npext.array(ens.encoders, min_dims=2, dtype=np.float64)
if ens.normalize_encoders:
encoders /= npext.norm(encoders, axis=1, keepdims=True)
# Build the neurons
gain, bias, max_rates, intercepts = get_gain_bias(ens, rng,
model.intercept_limit)
group = CxGroup(ens.n_neurons, label='%s' % ens)
group.bias[:] = bias
model.build(ens.neuron_type, ens.neurons, group)
# set default filter just in case no other filter gets set
group.configure_default_filter(model.inter_tau, dt=model.dt)
if ens.noise is not None:
raise NotImplementedError("Ensemble noise not implemented")
# Scale the encoders
if isinstance(ens.neuron_type, nengo.Direct):
raise NotImplementedError("Direct neurons not implemented")
# scaled_encoders = encoders
else:
# to keep scaling reasonable, we don't include the radius
# scaled_encoders = encoders * (gain / ens.radius)[:, np.newaxis]
scaled_encoders = encoders * gain[:, np.newaxis]
model.add_group(group)
model.objs[ens]['in'] = group
model.objs[ens]['out'] = group
model.objs[ens.neurons]['in'] = group
model.objs[ens.neurons]['out'] = group
model.params[ens] = BuiltEnsemble(eval_points=eval_points,
encoders=encoders,
intercepts=intercepts,
max_rates=max_rates,
scaled_encoders=scaled_encoders,
gain=gain,
bias=bias)
def get_gain_bias(ens, rng=np.random):
if ens.gain is not None and ens.bias is not None:
gain = get_samples(ens.gain, ens.n_neurons, rng=rng)
bias = get_samples(ens.bias, ens.n_neurons, rng=rng)
max_rates, intercepts = None, None # TODO: determine from gain & bias
elif ens.gain is not None or ens.bias is not None:
# TODO: handle this instead of error
raise NotImplementedError("gain or bias set for %s, but not both. "
"Solving for one given the other is not "
"implemented yet." % ens)
else:
max_rates = get_samples(ens.max_rates, ens.n_neurons, rng=rng)
intercepts = get_samples(ens.intercepts, ens.n_neurons, rng=rng)
gain, bias = ens.neuron_type.gain_bias(max_rates, intercepts)
if gain is not None and (not np.all(np.isfinite(gain))
or np.any(gain <= 0.)):
raise BuildError(
"The specified intercepts for %s lead to neurons with "
"negative or non-finite gain. Please adjust the intercepts so "
"that all gains are positive. For most neuron types (e.g., "
"LIF neurons) this is achieved by reducing the maximum "
"intercept value to below 1." % ens)
return gain, bias, max_rates, intercepts
def build_connection(model, conn):
"""Builds a `.Connection` object into a model.
A brief summary of what happens in the connection build process,
in order:
1. Solve for decoders.
2. Combine transform matrix with decoders to get weights.
3. Add operators for computing the function
or multiplying neural activity by weights.
4. Call build function for the synapse.
5. Call build function for the learning rule.
6. Add operator for applying learning rule delta to weights.
Some of these steps may be altered or omitted depending on the parameters
of the connection, in particular the pre and post types.
Parameters
----------
model : Model
The model to build into.
conn : Connection
The connection to build.
Notes
-----
Sets ``model.params[conn]`` to a `.BuiltConnection` instance.
"""
# Create random number generator
rng = np.random.RandomState(model.seeds[conn])
# Get input and output connections from pre and post
def get_prepost_signal(is_pre):
target = conn.pre_obj if is_pre else conn.post_obj
key = "out" if is_pre else "in"
if target not in model.sig:
raise BuildError(
"Building %s: the %r object %s is not in the "
"model, or has a size of zero." % (conn, "pre" if is_pre else "post", target)
)
if key not in model.sig[target]:
raise BuildError(
"Building %s: the %r object %s has a %r size of zero."
% (conn, "pre" if is_pre else "post", target, key)
)
return model.sig[target][key]
model.sig[conn]["in"] = get_prepost_signal(is_pre=True)
model.sig[conn]["out"] = get_prepost_signal(is_pre=False)
weights = None
eval_points = None
solver_info = None
signal_size = conn.size_out
post_slice = conn.post_slice
# Sample transform if given a distribution
transform = get_samples(conn.transform, conn.size_out, d=conn.size_mid, rng=rng)
# Figure out the signal going across this connection
in_signal = model.sig[conn]["in"]
if isinstance(conn.pre_obj, Node) or (
isinstance(conn.pre_obj, Ensemble) and isinstance(conn.pre_obj.neuron_type, Direct)
):
# Node or Decoded connection in directmode
weights = transform
sliced_in = slice_signal(model, in_signal, conn.pre_slice)
if conn.function is None:
in_signal = sliced_in
elif isinstance(conn.function, np.ndarray):
raise BuildError("Cannot use function points in direct connection")
else:
in_signal = Signal(np.zeros(conn.size_mid), name="%s.func" % conn)
model.add_op(SimPyFunc(in_signal, conn.function, None, sliced_in))
elif isinstance(conn.pre_obj, Ensemble): # Normal decoded connection
eval_points, weights, solver_info = build_decoders(model, conn, rng, transform)
if conn.solver.weights:
model.sig[conn]["out"] = model.sig[conn.post_obj.neurons]["in"]
signal_size = conn.post_obj.neurons.size_in
post_slice = Ellipsis # don't apply slice later
else:
weights = transform
in_signal = slice_signal(model, in_signal, conn.pre_slice)
if isinstance(conn.post_obj, Neurons):
weights = multiply(model.params[conn.post_obj.ensemble].gain[post_slice], weights)
# Add operator for applying weights
model.sig[conn]["weights"] = Signal(weights, name="%s.weights" % conn, readonly=True)
signal = Signal(np.zeros(signal_size), name="%s.weighted" % conn)
model.add_op(Reset(signal))
op = ElementwiseInc if weights.ndim < 2 else DotInc
model.add_op(op(model.sig[conn]["weights"], in_signal, signal, tag="%s.weights_elementwiseinc" % conn))
# Add operator for filtering
if conn.synapse is not None:
signal = model.build(conn.synapse, signal)
# Store the weighted-filtered output in case we want to probe it
model.sig[conn]["weighted"] = signal
# Copy to the proper slice
model.add_op(SlicedCopy(signal, model.sig[conn]["out"], dst_slice=post_slice, inc=True, tag="%s.gain" % conn))
# Build learning rules
if conn.learning_rule is not None:
rule = conn.learning_rule
rule = [rule] if not is_iterable(rule) else rule
targets = []
for r in itervalues(rule) if isinstance(rule, dict) else rule:
model.build(r)
targets.append(r.modifies)
if "encoders" in targets:
encoder_sig = model.sig[conn.post_obj]["encoders"]
if not any(isinstance(op, PreserveValue) and op.dst is encoder_sig for op in model.operators):
encoder_sig.readonly = False
model.add_op(PreserveValue(encoder_sig))
if "decoders" in targets or "weights" in targets:
if weights.ndim < 2:
raise BuildError("'transform' must be a 2-dimensional array for learning")
model.sig[conn]["weights"].readonly = False
model.add_op(PreserveValue(model.sig[conn]["weights"]))
model.params[conn] = BuiltConnection(
eval_points=eval_points, solver_info=solver_info, transform=transform, weights=weights
)
def build_ensemble(model, ens):
"""Builds an `.Ensemble` object into a model.
A brief summary of what happens in the ensemble build process, in order:
1. Generate evaluation points and encoders.
2. Normalize encoders to unit length.
3. Determine bias and gain.
4. Create neuron input signal
5. Add operator for injecting bias.
6. Call build function for neuron type.
7. Scale encoders by gain and radius.
8. Add operators for multiplying decoded input signal by encoders and
incrementing the result in the neuron input signal.
9. Call build function for injected noise.
Some of these steps may be altered or omitted depending on the parameters
of the ensemble, in particular the neuron type. For example, most steps are
omitted for the `.Direct` neuron type.
Parameters
----------
model : Model
The model to build into.
ens : Ensemble
The ensemble to build.
Notes
-----
Sets ``model.params[ens]`` to a `.BuiltEnsemble` instance.
"""
# Create random number generator
rng = np.random.RandomState(model.seeds[ens])
eval_points = gen_eval_points(ens, ens.eval_points, rng=rng)
# Set up signal
model.sig[ens]['in'] = Signal(np.zeros(ens.dimensions),
name="%s.signal" % ens)
model.add_op(Reset(model.sig[ens]['in']))
# Set up encoders
if isinstance(ens.neuron_type, Direct):
encoders = np.identity(ens.dimensions)
elif isinstance(ens.encoders, Distribution):
encoders = get_samples(
ens.encoders, ens.n_neurons, ens.dimensions, rng=rng)
else:
encoders = npext.array(ens.encoders, min_dims=2, dtype=np.float64)
if ens.normalize_encoders:
encoders /= npext.norm(encoders, axis=1, keepdims=True)
# Build the neurons
gain, bias, max_rates, intercepts = get_gain_bias(ens, rng)
if isinstance(ens.neuron_type, Direct):
model.sig[ens.neurons]['in'] = Signal(
np.zeros(ens.dimensions), name='%s.neuron_in' % ens)
model.sig[ens.neurons]['out'] = model.sig[ens.neurons]['in']
model.add_op(Reset(model.sig[ens.neurons]['in']))
else:
model.sig[ens.neurons]['in'] = Signal(
np.zeros(ens.n_neurons), name="%s.neuron_in" % ens)
model.sig[ens.neurons]['out'] = Signal(
np.zeros(ens.n_neurons), name="%s.neuron_out" % ens)
model.sig[ens.neurons]['bias'] = Signal(
bias, name="%s.bias" % ens, readonly=True)
model.add_op(Copy(model.sig[ens.neurons]['bias'],
model.sig[ens.neurons]['in']))
# This adds the neuron's operator and sets other signals
model.build(ens.neuron_type, ens.neurons)
# Scale the encoders
if isinstance(ens.neuron_type, Direct):
scaled_encoders = encoders
else:
scaled_encoders = encoders * (gain / ens.radius)[:, np.newaxis]
model.sig[ens]['encoders'] = Signal(
scaled_encoders, name="%s.scaled_encoders" % ens, readonly=True)
# Inject noise if specified
if ens.noise is not None:
model.build(ens.noise, sig_out=model.sig[ens.neurons]['in'], inc=True)
# Create output signal, using built Neurons
model.add_op(DotInc(
model.sig[ens]['encoders'],
model.sig[ens]['in'],
model.sig[ens.neurons]['in'],
tag="%s encoding" % ens))
# Output is neural output
model.sig[ens]['out'] = model.sig[ens.neurons]['out']
model.params[ens] = BuiltEnsemble(eval_points=eval_points,
encoders=encoders,
intercepts=intercepts,
max_rates=max_rates,
scaled_encoders=scaled_encoders,
gain=gain,
bias=bias)
def build_connection(model, conn):
"""Builds a `.Connection` object into a model.
A brief summary of what happens in the connection build process,
in order:
1. Solve for decoders.
2. Combine transform matrix with decoders to get weights.
3. Add operators for computing the function
or multiplying neural activity by weights.
4. Call build function for the synapse.
5. Call build function for the learning rule.
6. Add operator for applying learning rule delta to weights.
Some of these steps may be altered or omitted depending on the parameters
of the connection, in particular the pre and post types.
Parameters
----------
model : Model
The model to build into.
conn : Connection
The connection to build.
Notes
-----
Sets ``model.params[conn]`` to a `.BuiltConnection` instance.
"""
# Create random number generator
rng = np.random.RandomState(model.seeds[conn])
# Get input and output connections from pre and post
def get_prepost_signal(is_pre):
target = conn.pre_obj if is_pre else conn.post_obj
key = 'out' if is_pre else 'in'
if target not in model.sig:
raise BuildError("Building %s: the %r object %s is not in the "
"model, or has a size of zero." %
(conn, 'pre' if is_pre else 'post', target))
if key not in model.sig[target]:
raise BuildError(
"Building %s: the %r object %s has a %r size of zero." %
(conn, 'pre' if is_pre else 'post', target, key))
return model.sig[target][key]
model.sig[conn]['in'] = get_prepost_signal(is_pre=True)
model.sig[conn]['out'] = get_prepost_signal(is_pre=False)
weights = None
eval_points = None
solver_info = None
signal_size = conn.size_out
post_slice = conn.post_slice
# Sample transform if given a distribution
transform = get_samples(conn.transform,
conn.size_out,
d=conn.size_mid,
rng=rng)
# Figure out the signal going across this connection
in_signal = model.sig[conn]['in']
if (isinstance(conn.pre_obj, Node)
or (isinstance(conn.pre_obj, Ensemble)
and isinstance(conn.pre_obj.neuron_type, Direct))):
# Node or Decoded connection in directmode
weights = transform
sliced_in = slice_signal(model, in_signal, conn.pre_slice)
if conn.function is None:
in_signal = sliced_in
elif isinstance(conn.function, np.ndarray):
raise BuildError("Cannot use function points in direct connection")
else:
in_signal = Signal(np.zeros(conn.size_mid), name='%s.func' % conn)
model.add_op(SimPyFunc(in_signal, conn.function, None, sliced_in))
elif isinstance(conn.pre_obj, Ensemble): # Normal decoded connection
eval_points, weights, solver_info = model.build(
conn.solver, conn, rng, transform)
if conn.solver.weights:
model.sig[conn]['out'] = model.sig[conn.post_obj.neurons]['in']
signal_size = conn.post_obj.neurons.size_in
post_slice = None # don't apply slice later
else:
weights = transform
in_signal = slice_signal(model, in_signal, conn.pre_slice)
# Add operator for applying weights
model.sig[conn]['weights'] = Signal(weights,
name="%s.weights" % conn,
readonly=True)
signal = Signal(np.zeros(signal_size), name="%s.weighted" % conn)
model.add_op(Reset(signal))
op = ElementwiseInc if weights.ndim < 2 else DotInc
model.add_op(
op(model.sig[conn]['weights'],
in_signal,
signal,
tag="%s.weights_elementwiseinc" % conn))
# Add operator for filtering
if conn.synapse is not None:
signal = model.build(conn.synapse, signal)
# Store the weighted-filtered output in case we want to probe it
model.sig[conn]['weighted'] = signal
if isinstance(conn.post_obj, Neurons):
# Apply neuron gains (we don't need to do this if we're connecting to
# an Ensemble, because the gains are rolled into the encoders)
gains = Signal(model.params[conn.post_obj.ensemble].gain[post_slice],
name="%s.gains" % conn)
model.add_op(
ElementwiseInc(gains,
signal,
model.sig[conn]['out'][post_slice],
tag="%s.gains_elementwiseinc" % conn))
else:
# Copy to the proper slice
model.add_op(
Copy(signal,
model.sig[conn]['out'],
dst_slice=post_slice,
inc=True,
tag="%s" % conn))
# Build learning rules
if conn.learning_rule is not None:
rule = conn.learning_rule
rule = [rule] if not is_iterable(rule) else rule
targets = []
for r in itervalues(rule) if isinstance(rule, dict) else rule:
model.build(r)
targets.append(r.modifies)
if 'encoders' in targets:
encoder_sig = model.sig[conn.post_obj]['encoders']
encoder_sig.readonly = False
if 'decoders' in targets or 'weights' in targets:
if weights.ndim < 2:
raise BuildError(
"'transform' must be a 2-dimensional array for learning")
model.sig[conn]['weights'].readonly = False
model.params[conn] = BuiltConnection(eval_points=eval_points,
solver_info=solver_info,
transform=transform,
weights=weights)
def build_ensemble(model, ens):
"""Builds an `.Ensemble` object into a model.
A brief summary of what happens in the ensemble build process, in order:
1. Generate evaluation points and encoders.
2. Normalize encoders to unit length.
3. Determine bias and gain.
4. Create neuron input signal
5. Add operator for injecting bias.
6. Call build function for neuron type.
7. Scale encoders by gain and radius.
8. Add operators for multiplying decoded input signal by encoders and
incrementing the result in the neuron input signal.
9. Call build function for injected noise.
Some of these steps may be altered or omitted depending on the parameters
of the ensemble, in particular the neuron type. For example, most steps are
omitted for the `.Direct` neuron type.
Parameters
----------
model : Model
The model to build into.
ens : Ensemble
The ensemble to build.
Notes
-----
Sets ``model.params[ens]`` to a `.BuiltEnsemble` instance.
"""
# Create random number generator
rng = np.random.RandomState(model.seeds[ens])
eval_points = gen_eval_points(ens,
ens.eval_points,
rng=rng,
dtype=rc.float_dtype)
# Set up signal
model.sig[ens]["in"] = Signal(shape=ens.dimensions, name="%s.signal" % ens)
model.add_op(Reset(model.sig[ens]["in"]))
# Set up encoders
if isinstance(ens.neuron_type, Direct):
encoders = np.identity(ens.dimensions, dtype=rc.float_dtype)
elif isinstance(ens.encoders, Distribution):
encoders = get_samples(ens.encoders,
ens.n_neurons,
ens.dimensions,
rng=rng)
encoders = np.asarray(encoders, dtype=rc.float_dtype)
else:
encoders = npext.array(ens.encoders, min_dims=2, dtype=rc.float_dtype)
if ens.normalize_encoders:
encoders /= npext.norm(encoders, axis=1, keepdims=True)
if np.any(np.isnan(encoders)):
raise BuildError(
"NaNs detected in %r encoders. This usually means that you had zero-length "
"encoders that were normalized, resulting in NaNs. Ensure all encoders "
"have non-zero length, or set `normalize_encoders=False`." % ens)
# Build the neurons
gain, bias, max_rates, intercepts = get_gain_bias(ens,
rng,
dtype=rc.float_dtype)
if isinstance(ens.neuron_type, Direct):
model.sig[ens.neurons]["in"] = Signal(shape=ens.dimensions,
name="%s.neuron_in" % ens)
model.sig[ens.neurons]["out"] = model.sig[ens.neurons]["in"]
model.add_op(Reset(model.sig[ens.neurons]["in"]))
else:
model.sig[ens.neurons]["in"] = Signal(shape=ens.n_neurons,
name="%s.neuron_in" % ens)
model.sig[ens.neurons]["out"] = Signal(shape=ens.n_neurons,
name="%s.neuron_out" % ens)
model.sig[ens.neurons]["bias"] = Signal(bias,
name="%s.bias" % ens,
readonly=True)
model.add_op(
Copy(model.sig[ens.neurons]["bias"], model.sig[ens.neurons]["in"]))
# This adds the neuron's operator and sets other signals
model.build(ens.neuron_type, ens.neurons)
# Scale the encoders
if isinstance(ens.neuron_type, Direct):
scaled_encoders = encoders
else:
scaled_encoders = encoders * (gain / ens.radius)[:, np.newaxis]
model.sig[ens]["encoders"] = Signal(scaled_encoders,
name="%s.scaled_encoders" % ens,
readonly=True)
# Inject noise if specified
if ens.noise is not None:
model.build(ens.noise,
sig_out=model.sig[ens.neurons]["in"],
mode="inc")
# Create output signal, using built Neurons
model.add_op(
DotInc(
model.sig[ens]["encoders"],
model.sig[ens]["in"],
model.sig[ens.neurons]["in"],
tag="%s encoding" % ens,
))
# Output is neural output
model.sig[ens]["out"] = model.sig[ens.neurons]["out"]
model.params[ens] = BuiltEnsemble(
eval_points=eval_points,
encoders=encoders,
intercepts=intercepts,
max_rates=max_rates,
scaled_encoders=scaled_encoders,
gain=gain,
bias=bias,
)
def build_ensemble(model, ens):
if isinstance(ens.neuron_type, nengo.Direct):
raise NotImplementedError("Direct neurons not implemented")
# Create random number generator
rng = np.random.RandomState(model.seeds[ens])
eval_points = gen_eval_points(
ens, ens.eval_points, rng=rng, dtype=nengo.rc.float_dtype
)
# Set up encoders
if isinstance(ens.encoders, Distribution):
encoders = get_samples(ens.encoders, ens.n_neurons, ens.dimensions, rng=rng)
encoders = np.asarray(encoders, dtype=nengo.rc.float_dtype)
else:
encoders = npext.array(ens.encoders, min_dims=2, dtype=nengo.rc.float_dtype)
if ens.normalize_encoders:
encoders /= npext.norm(encoders, axis=1, keepdims=True)
if np.any(np.isnan(encoders)):
raise BuildError(
f"{ens}: NaNs detected in encoders. This usually means that you have "
"zero-length encoders; when normalized, these result in NaNs. Ensure all "
"encoders have non-zero length, or set `normalize_encoders=False`."
)
# Build the neurons
gain, bias, max_rates, intercepts = get_gain_bias(
ens, rng, intercept_limit=model.intercept_limit, dtype=nengo.rc.float_dtype
)
block = LoihiBlock(ens.n_neurons, label="%s" % ens)
block.compartment.bias[:] = bias
# build the neuron_type (see builders below)
model.build(ens.neuron_type, ens.neurons, block)
# set default filter just in case no other filter gets set
block.compartment.configure_default_filter(model.decode_tau, dt=model.dt)
if ens.noise is not None:
raise NotImplementedError("Ensemble noise not implemented")
# Scale the encoders
# we exclude the radius to keep scaling reasonable for decode neurons
scaled_encoders = encoders * gain[:, np.newaxis]
# add instructions for splitting
model.block_shapes[block] = model.config[ens].block_shape
model.add_block(block)
model.objs[ens]["in"] = block
model.objs[ens]["out"] = block
model.objs[ens.neurons]["in"] = block
model.objs[ens.neurons]["out"] = block
model.params[ens] = BuiltEnsemble(
eval_points=eval_points,
encoders=encoders,
intercepts=intercepts,
max_rates=max_rates,
scaled_encoders=scaled_encoders,
gain=gain,
bias=bias,
)
def build_connection(model, conn):
if isinstance(conn.transform, conv.Conv2D):
# TODO: integrate these into the same function
conv.build_conv2d_connection(model, conn)
return
# Create random number generator
rng = np.random.RandomState(model.seeds[conn])
pre_cx = model.objs[conn.pre_obj]['out']
post_cx = model.objs[conn.post_obj]['in']
assert isinstance(pre_cx, (CxGroup, CxSpikeInput))
assert isinstance(post_cx, (CxGroup, CxProbe))
weights = None
eval_points = None
solver_info = None
neuron_type = None
# Sample transform if given a distribution
transform = get_samples(conn.transform,
conn.size_out,
d=conn.size_mid,
rng=rng)
tau_s = 0.0 # `synapse is None` gets mapped to `tau_s = 0.0`
if isinstance(conn.synapse, nengo.synapses.Lowpass):
tau_s = conn.synapse.tau
elif conn.synapse is not None:
raise NotImplementedError("Cannot handle non-Lowpass synapses")
needs_interneurons = False
if isinstance(conn.pre_obj, Node):
assert conn.pre_slice == slice(None)
if np.array_equal(transform, np.array(1.)):
# TODO: this identity transform may be avoidable
transform = np.eye(conn.pre.size_out)
else:
assert transform.ndim == 2, "transform shape not handled yet"
assert transform.shape[1] == conn.pre.size_out
assert transform.shape[1] == conn.pre.size_out
if isinstance(conn.pre_obj, ChipReceiveNeurons):
weights = transform / model.dt
neuron_type = conn.pre_obj.neuron_type
else:
# input is on-off neuron encoded, so double/flip transform
weights = np.column_stack([transform, -transform])
# (max_rate = INTER_RATE * INTER_N) is the spike rate we
# use to represent a value of +/- 1
weights = weights * model.inter_scale
elif (isinstance(conn.pre_obj, Ensemble)
and isinstance(conn.pre_obj.neuron_type, nengo.Direct)):
raise NotImplementedError()
elif isinstance(conn.pre_obj, Ensemble): # Normal decoded connection
eval_points, weights, solver_info = model.build(
conn.solver, conn, rng, transform)
# the decoder solver assumes a spike height of 1/dt; that isn't the
# case on loihi, so we need to undo that scaling
weights = weights / model.dt
neuron_type = conn.pre_obj.neuron_type
if not conn.solver.weights:
needs_interneurons = True
elif isinstance(conn.pre_obj, Neurons):
assert conn.pre_slice == slice(None)
assert transform.ndim == 2, "transform shape not handled yet"
weights = transform / model.dt
neuron_type = conn.pre_obj.ensemble.neuron_type
else:
raise NotImplementedError("Connection from type %r" %
(type(conn.pre_obj), ))
if neuron_type is not None and hasattr(neuron_type, 'amplitude'):
weights = weights * neuron_type.amplitude
mid_cx = pre_cx
mid_axon_inds = None
post_tau = tau_s
if needs_interneurons and not isinstance(conn.post_obj, Neurons):
# --- add interneurons
assert weights.ndim == 2
d, n = weights.shape
if isinstance(post_cx, CxProbe):
# use non-spiking interneurons for voltage probing
assert post_cx.target is None
assert conn.post_slice == slice(None)
# use the same scaling as the ensemble does, to get good
# decodes. Note that this assumes that the decoded value
# is in the range -radius to radius, which is usually true.
weights = weights / conn.pre_obj.radius
gain = 1 # model.dt * INTER_RATE(=1000)
dec_cx = CxGroup(2 * d, label='%s' % conn, location='core')
dec_cx.configure_nonspiking(dt=model.dt, vth=model.vth_nonspiking)
dec_cx.bias[:] = 0
model.add_group(dec_cx)
model.objs[conn]['decoded'] = dec_cx
dec_syn = CxSynapses(n, label="probe_decoders")
weights2 = gain * np.vstack([weights, -weights]).T
else:
# use spiking interneurons for on-chip connection
post_d = conn.post_obj.size_in
post_inds = np.arange(post_d, dtype=np.int32)[conn.post_slice]
assert len(post_inds) == conn.size_out == d
mid_axon_inds = np.hstack([post_inds, post_inds + post_d] *
model.inter_n)
gain = model.dt * model.inter_rate
dec_cx = CxGroup(2 * d * model.inter_n,
label='%s' % conn,
location='core')
dec_cx.configure_relu(dt=model.dt)
dec_cx.bias[:] = 0.5 * gain * np.array(
([1.] * d + [1.] * d) * model.inter_n)
if model.inter_noise_exp > -30:
dec_cx.enableNoise[:] = 1
dec_cx.noiseExp0 = model.inter_noise_exp
dec_cx.noiseAtDendOrVm = 1
model.add_group(dec_cx)
model.objs[conn]['decoded'] = dec_cx
if isinstance(conn.post_obj, Ensemble):
# loihi encoders don't include radius, so handle scaling here
weights = weights / conn.post_obj.radius
dec_syn = CxSynapses(n, label="decoders")
weights2 = 0.5 * gain * np.vstack(
[weights, -weights] * model.inter_n).T
# use tau_s for filter into interneurons, and INTER_TAU for filter out
dec_cx.configure_filter(tau_s, dt=model.dt)
post_tau = model.inter_tau
dec_syn.set_full_weights(weights2)
dec_cx.add_synapses(dec_syn)
model.objs[conn]['decoders'] = dec_syn
dec_ax0 = CxAxons(n, label="decoders")
dec_ax0.target = dec_syn
pre_cx.add_axons(dec_ax0)
model.objs[conn]['decode_axons'] = dec_ax0
if conn.learning_rule_type is not None:
if isinstance(conn.learning_rule_type, nengo.PES):
pes_learn_rate = conn.learning_rule_type.learning_rate
# scale learning rates to roughly match Nengo
# 1e-4 is the Nengo core default learning rate
pes_learn_rate *= 4 / 1e-4
assert isinstance(conn.learning_rule_type.pre_synapse,
nengo.synapses.Lowpass)
pes_pre_syn = conn.learning_rule_type.pre_synapse.tau
# scale pre_syn.tau from s to ms
pes_pre_syn *= 1e3
dec_syn.set_learning(tracing_tau=pes_pre_syn,
tracing_mag=pes_learn_rate)
else:
raise NotImplementedError()
mid_cx = dec_cx
if isinstance(post_cx, CxProbe):
assert post_cx.target is None
assert conn.post_slice == slice(None)
post_cx.target = mid_cx
mid_cx.add_probe(post_cx)
elif isinstance(conn.post_obj, Neurons):
assert isinstance(post_cx, CxGroup)
assert conn.post_slice == slice(None)
if weights is None:
raise NotImplementedError("Need weights for connection to neurons")
else:
assert weights.ndim == 2
n2, n1 = weights.shape
assert post_cx.n == n2
syn = CxSynapses(n1, label="neuron_weights")
gain = model.params[conn.post_obj.ensemble].gain
syn.set_full_weights(weights.T * gain)
post_cx.add_synapses(syn)
model.objs[conn]['weights'] = syn
ax = CxAxons(mid_cx.n, label="neuron_weights")
ax.target = syn
mid_cx.add_axons(ax)
post_cx.configure_filter(post_tau, dt=model.dt)
if conn.learning_rule_type is not None:
raise NotImplementedError()
elif isinstance(conn.post_obj, Ensemble) and conn.solver.weights:
assert isinstance(post_cx, CxGroup)
assert weights.ndim == 2
n2, n1 = weights.shape
assert post_cx.n == n2
# loihi encoders don't include radius, so handle scaling here
weights = weights / conn.post_obj.radius
syn = CxSynapses(n1, label="%s::decoder_weights" % conn)
syn.set_full_weights(weights.T)
post_cx.add_synapses(syn)
model.objs[conn]['weights'] = syn
ax = CxAxons(n1, label="decoder_weights")
ax.target = syn
mid_cx.add_axons(ax)
post_cx.configure_filter(post_tau, dt=model.dt)
if conn.learning_rule_type is not None:
raise NotImplementedError()
elif isinstance(conn.post_obj, Ensemble):
if 'inter_encoders' not in post_cx.named_synapses:
build_interencoders(model, conn.post_obj)
mid_ax = CxAxons(mid_cx.n, label="encoders")
mid_ax.target = post_cx.named_synapses['inter_encoders']
mid_ax.set_axon_map(mid_axon_inds)
mid_cx.add_axons(mid_ax)
model.objs[conn]['mid_axons'] = mid_ax
post_cx.configure_filter(post_tau, dt=model.dt)
elif isinstance(conn.post_obj, Node):
raise NotImplementedError()
else:
raise NotImplementedError()
model.params[conn] = BuiltConnection(eval_points=eval_points,
solver_info=solver_info,
transform=transform,
weights=weights)
def build_connection(model, conn):
if isinstance(conn.transform, conv.Conv2D):
# TODO: integrate these into the same function
conv.build_conv2d_connection(model, conn)
return
# Create random number generator
rng = np.random.RandomState(model.seeds[conn])
pre_cx = model.objs[conn.pre_obj]['out']
post_cx = model.objs[conn.post_obj]['in']
assert isinstance(pre_cx, (CxGroup, CxSpikeInput))
assert isinstance(post_cx, (CxGroup, CxProbe))
weights = None
eval_points = None
solver_info = None
neuron_type = None
# Sample transform if given a distribution
transform = get_samples(
conn.transform, conn.size_out, d=conn.size_mid, rng=rng)
tau_s = 0.0 # `synapse is None` gets mapped to `tau_s = 0.0`
if isinstance(conn.synapse, nengo.synapses.Lowpass):
tau_s = conn.synapse.tau
elif conn.synapse is not None:
raise NotImplementedError("Cannot handle non-Lowpass synapses")
needs_decode_neurons = False
target_encoders = None
if isinstance(conn.pre_obj, Node):
assert conn.pre_slice == slice(None)
if np.array_equal(transform, np.array(1.)):
# TODO: this identity transform may be avoidable
transform = np.eye(conn.pre.size_out)
else:
assert transform.ndim == 2, "transform shape not handled yet"
assert transform.shape[1] == conn.pre.size_out
assert transform.shape[1] == conn.pre.size_out
if isinstance(conn.pre_obj, ChipReceiveNeurons):
weights = transform / model.dt
neuron_type = conn.pre_obj.neuron_type
else:
# input is on-off neuron encoded, so double/flip transform
weights = np.column_stack([transform, -transform])
target_encoders = 'node_encoders'
elif (isinstance(conn.pre_obj, Ensemble)
and isinstance(conn.pre_obj.neuron_type, nengo.Direct)):
raise NotImplementedError()
elif isinstance(conn.pre_obj, Ensemble): # Normal decoded connection
eval_points, weights, solver_info = model.build(
conn.solver, conn, rng, transform)
# the decoder solver assumes a spike height of 1/dt; that isn't the
# case on loihi, so we need to undo that scaling
weights = weights / model.dt
neuron_type = conn.pre_obj.neuron_type
if not conn.solver.weights:
needs_decode_neurons = True
elif isinstance(conn.pre_obj, Neurons):
assert conn.pre_slice == slice(None)
assert transform.ndim == 2, "transform shape not handled yet"
weights = transform / model.dt
neuron_type = conn.pre_obj.ensemble.neuron_type
else:
raise NotImplementedError("Connection from type %r" % (
type(conn.pre_obj),))
if neuron_type is not None and hasattr(neuron_type, 'amplitude'):
weights = weights * neuron_type.amplitude
mid_cx = pre_cx
mid_axon_inds = None
post_tau = tau_s
if needs_decode_neurons and not isinstance(conn.post_obj, Neurons):
# --- add decode neurons
assert weights.ndim == 2
d, n = weights.shape
if isinstance(post_cx, CxProbe):
# use non-spiking decode neurons for voltage probing
assert post_cx.target is None
assert conn.post_slice == slice(None)
# use the same scaling as the ensemble does, to get good
# decodes. Note that this assumes that the decoded value
# is in the range -radius to radius, which is usually true.
weights = weights / conn.pre_obj.radius
gain = 1
dec_cx = CxGroup(2 * d, label='%s' % conn, location='core')
dec_cx.configure_nonspiking(dt=model.dt, vth=model.vth_nonspiking)
dec_cx.bias[:] = 0
model.add_group(dec_cx)
model.objs[conn]['decoded'] = dec_cx
dec_syn = CxSynapses(n, label="probe_decoders")
weights2 = gain * np.vstack([weights, -weights]).T
dec_syn.set_full_weights(weights2)
dec_cx.add_synapses(dec_syn)
model.objs[conn]['decoders'] = dec_syn
else:
# use spiking decode neurons for on-chip connection
if isinstance(conn.post_obj, Ensemble):
# loihi encoders don't include radius, so handle scaling here
weights = weights / conn.post_obj.radius
post_d = conn.post_obj.size_in
post_inds = np.arange(post_d, dtype=np.int32)[conn.post_slice]
assert weights.shape[0] == len(post_inds) == conn.size_out == d
mid_axon_inds = model.decode_neurons.get_post_inds(
post_inds, post_d)
target_encoders = 'decode_neuron_encoders'
dec_cx, dec_syn = model.decode_neurons.get_cx(
weights, cx_label="%s" % conn, syn_label="decoders")
model.add_group(dec_cx)
model.objs[conn]['decoded'] = dec_cx
model.objs[conn]['decoders'] = dec_syn
# use tau_s for filter into decode neurons, decode_tau for filter out
dec_cx.configure_filter(tau_s, dt=model.dt)
post_tau = model.decode_tau
dec_ax0 = CxAxons(n, label="decoders")
dec_ax0.target = dec_syn
pre_cx.add_axons(dec_ax0)
model.objs[conn]['decode_axons'] = dec_ax0
if conn.learning_rule_type is not None:
rule_type = conn.learning_rule_type
if isinstance(rule_type, nengo.PES):
if not isinstance(rule_type.pre_synapse,
nengo.synapses.Lowpass):
raise ValidationError(
"Loihi only supports `Lowpass` pre-synapses for "
"learning rules", attr='pre_synapse', obj=rule_type)
tracing_tau = rule_type.pre_synapse.tau / model.dt
# Nengo builder scales PES learning rate by `dt / n_neurons`
n_neurons = (conn.pre_obj.n_neurons
if isinstance(conn.pre_obj, Ensemble)
else conn.pre_obj.size_in)
learning_rate = rule_type.learning_rate * model.dt / n_neurons
# Account for scaling to put integer error in range [-127, 127]
learning_rate /= model.pes_error_scale
# Tracing mag set so that the magnitude of the pre trace
# is independent of the pre tau. `dt` factor accounts for
# Nengo's `dt` spike scaling. Where is the second `dt` from?
# Maybe the fact that post decode neurons have `vth = 1/dt`?
tracing_mag = -np.expm1(-1. / tracing_tau) / model.dt**2
# learning weight exponent controls the maximum weight
# magnitude/weight resolution
wgt_exp = model.pes_wgt_exp
dec_syn.set_learning(
learning_rate=learning_rate,
tracing_mag=tracing_mag,
tracing_tau=tracing_tau,
wgt_exp=wgt_exp,
)
else:
raise NotImplementedError()
mid_cx = dec_cx
if isinstance(post_cx, CxProbe):
assert post_cx.target is None
assert conn.post_slice == slice(None)
post_cx.target = mid_cx
mid_cx.add_probe(post_cx)
elif isinstance(conn.post_obj, Neurons):
assert isinstance(post_cx, CxGroup)
assert conn.post_slice == slice(None)
if weights is None:
raise NotImplementedError("Need weights for connection to neurons")
else:
assert weights.ndim == 2
n2, n1 = weights.shape
assert post_cx.n == n2
syn = CxSynapses(n1, label="neuron_weights")
gain = model.params[conn.post_obj.ensemble].gain
syn.set_full_weights(weights.T * gain)
post_cx.add_synapses(syn)
model.objs[conn]['weights'] = syn
ax = CxAxons(mid_cx.n, label="neuron_weights")
ax.target = syn
mid_cx.add_axons(ax)
post_cx.configure_filter(post_tau, dt=model.dt)
if conn.learning_rule_type is not None:
raise NotImplementedError()
elif isinstance(conn.post_obj, Ensemble) and conn.solver.weights:
assert isinstance(post_cx, CxGroup)
assert weights.ndim == 2
n2, n1 = weights.shape
assert post_cx.n == n2
# loihi encoders don't include radius, so handle scaling here
weights = weights / conn.post_obj.radius
syn = CxSynapses(n1, label="%s::decoder_weights" % conn)
syn.set_full_weights(weights.T)
post_cx.add_synapses(syn)
model.objs[conn]['weights'] = syn
ax = CxAxons(n1, label="decoder_weights")
ax.target = syn
mid_cx.add_axons(ax)
post_cx.configure_filter(post_tau, dt=model.dt)
if conn.learning_rule_type is not None:
raise NotImplementedError()
elif isinstance(conn.post_obj, Ensemble):
assert target_encoders is not None
if target_encoders not in post_cx.named_synapses:
build_decode_neuron_encoders(
model, conn.post_obj, kind=target_encoders)
mid_ax = CxAxons(mid_cx.n, label="encoders")
mid_ax.target = post_cx.named_synapses[target_encoders]
mid_ax.set_axon_map(mid_axon_inds)
mid_cx.add_axons(mid_ax)
model.objs[conn]['mid_axons'] = mid_ax
post_cx.configure_filter(post_tau, dt=model.dt)
elif isinstance(conn.post_obj, Node):
raise NotImplementedError()
else:
raise NotImplementedError()
model.params[conn] = BuiltConnection(
eval_points=eval_points,
solver_info=solver_info,
transform=transform,
weights=weights)
