1. 程式人生 > >卷積神經網絡要點解析

卷積神經網絡要點解析

pla 玩轉 iframe chan ref ram social lar href

參照:
[stanford]Convolutional Neural Networks (CNNs / ConvNets)
[karpathy]ConvNetJS CIFAR-10 demo
【知乎】沒有博士學位,照樣玩轉TensorFlow深度學習
【視頻】TensorFlow and deep learning, without a PhD

Architecture Overview

  • why ConvNet ?

    Regular Neural Nets don’t scale well to full images. In CIFAR-10, images are only of size 32x32x3 (32 wide, 32 high, 3 color channels), so a single fully-connected neuron

    in a first hidden
    layer of a regular Neural Network would have 32*32*3 = 3072 weights.

卷積神經網絡要點解析