Android 台灣中文網 › 標籤 › 加法

標籤: 加法

相關帖子	版塊	作者	回覆/查看	最後發表

	從加法開始的極簡生活作者：澀谷直人 (繁_PDF)	Android 手機小說	wdiezs 2024-6-6	102 6545	lcyingying 2026-2-18 08:51
	財富自由的整理鍊金術作者：小印 (繁_PDF)	Android 手機小說	wdiezs 2024-6-10	100 6453	plusaa 2024-11-18 13:51

更多...

相關日誌

分享 rnn 八位元二進制加法: 嵐風 2021-7-9 11:55; import copy, numpy as np np.random.seed(0) # compute sigmoid nonlinearity def sigmoid(x): output = 1/(1+np.exp(-x)) return output # convert output of sigmoid function to its derivative def sigmoid_output_to_derivative(output): return output*(1-output) # training dataset generation int2binary = {} binary_dim = 8 largest_number = pow(2,binary_dim) binary = np.unpackbits(np.array( ,dtype=np.uint8).T,axis=1) for i in range(largest_number): int2binary = binary # input variables alpha = 0.3 input_dim = 2 hidden_dim = 16 output_dim = 1 # initialize neural network weights synapse_0 = 2*np.random.random((input_dim,hidden_dim)) - 1 synapse_1 = 2*np.random.random((hidden_dim,output_dim)) - 1 synapse_h = 2*np.random.random((hidden_dim,hidden_dim)) - 1 synapse_0_update = np.zeros_like(synapse_0) synapse_1_update = np.zeros_like(synapse_1) synapse_h_update = np.zeros_like(synapse_h) # training logic for j in range(10000): # generate a simple addition problem (a + b = c) a_int = np.random.randint(largest_number/2) # int version a = int2binary # binary encoding b_int = np.random.randint(largest_number/2) # int version b = int2binary # binary encoding # true answer c_int = a_int + b_int c = int2binary # where we"ll store our best guess (binary encoded) d = np.zeros_like(c) overallError = 0 layer_2_deltas = list() layer_1_values = list() layer_1_values.append(np.zeros(hidden_dim)) # moving along the positions in the binary encoding for position in range(binary_dim): # generate input and output X = np.array( ,b ]]) y = np.array( ]]).T # hidden layer (input ~+ prev_hidden) layer_1 = sigmoid(np.dot(X,synapse_0) + np.dot(layer_1_values ,synapse_h)) # output layer (new binary representation) layer_2 = sigmoid(np.dot(layer_1,synapse_1)) # did we miss?... if so by how much? layer_2_error = y - layer_2 layer_2_deltas.append((layer_2_error)*sigmoid_output_to_derivative(layer_2)) overallError += np.abs(layer_2_error ) # decode estimate so we can print it out d = np.round(layer_2 ) # store hidden layer so we can use it in the next timestep layer_1_values.append(copy.deepcopy(layer_1)) future_layer_1_delta = np.zeros(hidden_dim) for position in range(binary_dim): X = np.array( ,b ]]) layer_1 = layer_1_values prev_layer_1 = layer_1_values # error at output layer layer_2_delta = layer_2_deltas # error at hidden layer layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(synapse_1.T)) * sigmoid_output_to_derivative(layer_1) # let"s update all our weights so we can try again synapse_1_update += np.atleast_2d(layer_1).T.dot(layer_2_delta) synapse_h_update += np.atleast_2d(prev_layer_1).T.dot(layer_1_delta) synapse_0_update += X.T.dot(layer_1_delta) future_layer_1_delta = layer_1_delta synapse_0 += synapse_0_update * alpha synapse_1 += synapse_1_update * alpha synapse_h += synapse_h_update * alpha synapse_0_update *= 0 synapse_1_update *= 0 synapse_h_update *= 0 # print out progress if(j % 1000 == 0): print("誤差： "+str(overallError)) print("預測： "+str(d)) print("實際： "+str(c)) out = 0 for index,x in enumerate(reversed(d)): out += x*pow(2,index) print(str(a_int) + " + " + str(b_int) + " = " + str(out)) print("------------"); 142 次閱讀|0 個評論

更多...

標籤: 加法

相關帖子

相關日誌