def objective_U():
targets = { 'f':quadratic_Poisson, 'barrier':eig_barrier }
targets = kolia_theano.reparameterize(targets,UVs(NRGC))
list_targets= kolia_theano.reparameterize({'eigsM':eigsM, 'invM':invM },UVs(NRGC),
reducer=lambda r,x: r + [x], zero=[])
targets.update( list_targets )
return kolia_theano.Objective( init_params={'U': U }, differentiate=['f'], **targets )
def objective_UV1():
targets = { 'f':quadratic_Poisson, 'barrier':eig_pos_barrier }
targets = kolia_theano.reparameterize(targets,UVs(NRGC))
return kolia_theano.Objective( init_params={'V1': R['V'] , 'U': R['U'] }, differentiate=['f'],
mode='FAST_RUN' , **targets )
(N_spikes,STA,STC), U, V1, bbar, Cb , STAB = simulate_data.LNLNP(NL=NL,N=24)
Nsub, Ncone = U.shape
NRGC, Nsub = V1.shape
def callback( objective , params ):
print 'Objective: ' , objective.f(params) , ' barrier: ', objective.barrier(params)
true = {'U' : U , 'V1': V1 }
data = {'STAs':np.vstack(STA) , 'STCs':np.vstack([stc[np.newaxis,:] for stc in STC]),
'V2':V2*np.ones(Nsub) , 'N':NRGC }
targets = { 'f':quadratic_Poisson, 'barrier':eig_barrier }
targets = kolia_theano.reparameterize(targets,UVs(NRGC))
objective = kolia_theano.Objective( init_params=true, differentiate=['f'],
callback=callback, **targets )
optimizer = optimize.optimizer( objective.where(**data) )
trupar = true
for i in range(2):
trupar = optimizer(init_params=trupar)
trupar = objective.unflat(trupar)
init_params = {'U' : 0.0001+0.05*R.random(size=U.shape ) ,
'V1': 0.0001+0.05*R.random(size=V1.shape) }