Neural Networks and Deep Learning
What this book is about
On the exercises and problems
Using neural nets to recognize handwritten digits
How the backpropagation algorithm works
Improving the way neural networks learn
A visual proof that neural nets can compute any function
Why are deep neural networks hard to train?
Deep learning
Appendix: Is there a simple algorithm for intelligence?
Acknowledgements
Frequently Asked Questions
· · · · · · (收起)
What this book is about
On the exercises and problems
Using neural nets to recognize handwritten digits
How the backpropagation algorithm works
Improving the way neural networks learn
A visual proof that neural nets can compute any function
Why are deep neural networks hard to train?
Deep learning
Appendix: Is there a simple algorithm for intelligence?
Acknowledgements
Frequently Asked Questions
· · · · · · (收起)
具体描述
http://neuralnetworksanddeeplearning.com/
用户评价
评分
##我没有机器，也不想学习😂
评分
##挺不错的神经网络的入门书，从理论到代码，看得出经过精心的裁剪。对基本概念和原理介绍得不错，虽然有很多数学公式，但python的代码帮助理解很多细节。激活函数、代价函数、随机梯度下降、反向传播、过度拟合和规范化、权重初始化、超参数优化、卷积网络的局部感受野、混合层、特征映射。
评分
非常好的入门书籍。作者从头到尾都在给你做心灵按摩：don't worry,it's simple.don't panic,it's easy.stop feeling stupid about yourself,just move forward.
评分
##数学苦手的程序猿，读这本书启蒙一下挺好
评分
##翻译版本，讲例子还蛮深入浅出。
评分
##我没有机器，也不想学习😂
评分
##物理学家写的深度学习方面的书，直觉很好。
评分
##极好极好极好的书，如果对机器学习感兴趣，是必读的书。甚至完全不需要数学基础。
##一本非常非常棒的神经网络和深度学习的入门书，真正当然得起深入浅出，通过简洁明了的数学推导，和清晰明了简短的代码，把神经网络和CNN做了非常易懂的介绍，强烈推荐深度学习第一书。