def __init__(self, Wx, Wh, b, stateful=False):
self.params = [Wx, Wh, b]
self.grads = [np.zeros_like(Wx), np.zeros_like(Wh), np.zeros_like(b)]
self.layers = None
self.h, self.dh = None, None
self.stateful = stateful
def __init__(self, Wx, Wh, b):
'''
Parameters
----------
Wx: 入力`x`用の重みパラーメタ（4つ分の重みをまとめる）
Wh: 隠れ状態`h`用の重みパラメータ（4つ分の重みをまとめる）
b: バイアス（4つ分のバイアスをまとめる）
'''
self.params = [Wx, Wh, b]
self.grads = [np.zeros_like(Wx), np.zeros_like(Wh), np.zeros_like(b)]
self.cache = None
def backward(self, dh):
dhs = np.zeros_like(self.hs)
dhs[:, -1, :] = dh
dout = self.lstm.backward(dhs)
self.embed.backward(dout)
return None
def update(self, params, grads):
if self.m is None:
self.m, self.v = [], []
for param in params:
self.m.append(np.zeros_like(param))
self.v.append(np.zeros_like(param))
self.iter += 1
for i in range(len(params)):
self.m[i] = self.beta1 * self.m[i] + (1 - self.beta1) * grads[i]
self.v[i] = self.beta2 * self.v[i] + (1 - self.beta2) * (grads[i]**
2)
m_i_hat = self.m[i] / (1 - self.beta1**self.iter)
v_i_hat = self.v[i] / (1 - self.beta2**self.iter)
params[i] -= self.lr * m_i_hat / (np.sqrt(v_i_hat) + 1e-8)
def ppmi(C, verbose=False, eps=1e-8):
'''PPMI（正の相互情報量）の作成
:param C: 共起行列
:param verbose: 進行状況を出力するかどうか
:return:
'''
M = np.zeros_like(C, dtype=np.float32)
N = np.sum(C)
S = np.sum(C, axis=0)
total = C.shape[0] * C.shape[1]
cnt = 0
for i in range(C.shape[0]):
for j in range(C.shape[1]):
pmi = np.log2(C[i, j] * N / (S[i] * S[j]) + eps)
M[i, j] = max(0, pmi)
if verbose:
cnt += 1
if cnt % (total // 100) == 0:
print('%.1f%% done' % (100 * cnt / total))
return M
def __init__(self, Wx, Wh, b):
self.params = [Wx, Wh, b]
self.grads = [np.zeros_like(Wx), np.zeros_like(Wh), np.zeros_like(b)]
self.cache = None
def __init__(self, W, b):
self.params = [W, b]
self.grads = [np.zeros_like(W), np.zeros_like(b)]
self.x = None
def __init__(self, W):
self.params = [W]
self.grads = [np.zeros_like(W)]
self.layers = None
self.W = W
def __init__(self, W):
self.params = [W]
self.grads = [np.zeros_like(W)]
self.x = None
