Android 台灣中文網 › 標籤 › 位元

標籤: 位元

相關帖子	版塊	作者	回覆/查看	最後發表

與WIN7 64位元連結	Xperia L C2105	chenkim 2013-9-13	2 1003	exp5201 2013-9-14 11:00
1909 win7 64位元驅動	i909 SPhone	ass21766h 2013-10-20	10 4439	dorakitt 2016-2-16 03:46
Nexus 8採64位元處理器代號HTC T1	Android 新機資訊	zzccxxvv1122 2014-8-9	13 2551	黃振堯 2014-8-22 21:42
ESET Smart Security 2016雙位元	Windows 軟體下載	tailiabs 2016-1-20	85 19963	meggieko 2019-1-23 12:04
萬艦齊發：卡拉克沙漠 64位元版(PC@簡中@[email protected])	高閱讀權限下載區	溫柔海洋 2016-1-27	0 1283	溫柔海洋 2015-1-10 22:39
救火者整合5號升級檔 64位元版(PC@簡中@[email protected])	高閱讀權限下載區	溫柔海洋 2016-2-23	0 565	溫柔海洋 2015-1-10 22:32
Armello/愛門羅 64位元版官方中文(PC@簡中@MG@796MB)	高閱讀權限下載區	溫柔海洋 2016-4-11	0 3505	溫柔海洋 2015-1-10 22:28
我現在電腦是win7 32位元,但我想灌win7 64位元的?	已解決或取消懸賞	leonllll 2016-4-21	16 2308	蔡孟翰xd 2016-4-25 20:14
紅米Note2在win7 64位元抓不到	紅米Note 2/Note 3	ahs 2016-5-14	0 3213	ahs 2016-5-14 14:19
AVG Internet Security 16.71 雙位元	Windows 軟體下載	阿給事我遊戲 2016-8-10	9 2211	索超 2017-3-16 22:11
WinRAR 5.4.0 正式版 (32/64位元)	Windows 軟體下載	kit654 2016-8-21	117 15926	sky20029105 2018-1-31 20:56
MSniper 32位元使用問題	Pokémon GO	f830203 2016-9-12	3 1071	concise 2016-11-18 03:25
請問哪有win7 32位元的版本	Windows 軟體交流	linasuperq 2017-3-2	11 2395	BooFey 2017-3-13 11:24
一鍵安裝win7跟win8.1雙位元 5月份安全性更新檔	Windows 軟體下載	o夢天使o 2017-5-15	24 4716	JOEY1978 2019-11-6 04:11
3ds Max 2018 多國語雙位元板(2022補檔)	Windows 軟體下載	匿名 2017-9-4	600 200060	dabay 2025-1-8 13:50
如何設置系統色彩品質為32位元全彩色	遊戲模擬器交流	892011476 2018-1-4	0 2929	892011476 2018-1-4 10:29
win 7 繁中純淨版64位元萬用ghost(已啟動產品金鑰)	Windows 軟體下載	趙育陞 2018-7-16	34 27101	suke1387 2019-10-15 18:45
win 7 繁中整合版64位元萬用ghost(已啟動產品金鑰)	Windows 軟體下載	趙育陞 2018-7-17	38 12776	mina.chao 2020-5-2 12:55
win 7 繁中純淨版32位元萬用ghost(已啟動產品金鑰)	Windows 軟體下載	趙育陞 2018-7-23	8 5501	wayhome99 2018-11-19 12:28
win 7 繁中整合版32位元萬用ghost(已啟動產品金鑰)	Windows 軟體下載	趙育陞 2018-7-23	5 8027	kenwong1 2020-2-1 16:14

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("------------"); 140 次閱讀|0 個評論

更多...

標籤: 位元

相關帖子

相關日誌