Skip to content

revsic/numpy-rnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

numpy-RNN

numpy implementation of Recurrent Neural Networks

Recurrent Neural Networks

Training Vanilla RNN for binary addition.

largest = pow(2, BIN_DIM)
decimal = np.array([range(largest)]).astype(np.uint8).T
binary = np.unpackbits(decimal, axis=1)

Simply prepare the binary digit database. And propagate forward and backward to train binary addition.

hidden = sigmoid(np.dot(X, w0) + np.dot(hidden_values[-1], wh))
output = sigmoid(np.dot(hidden, w1))

pred[pos] = np.round(output[0][0])

Training was successful with 100% accuracy.

----------
Iter 9000
Error : [ 0.68126419]
Pred : [1 0 1 0 1 0 0 0]
True : [1 0 1 0 1 0 0 0]
108 + 60 = 168
----------

LSTM Networks

Training LSTM RNN for mnist handwritten digit recognition.

mnist = tf.keras.datasets.mnist
(train_x, train_y), _ = mnist.load_data()

Prepare the mnist digit database with tf.keras.datasets.mnist.

caches, states = LSTM_Cell(Xt)
c, h = states[-1]

out = np.dot(h, wy) + by
pred = softmax(out)
entropy = cross_entropy(pred, Y)

Train the LSTM model with BPTT and it was successful to recognize handwritten digits.

About

numpy implementation of Recurrent Neural Network

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published