datawhalechina / d2l-ai-solutions-manual Goto Github PK
View Code? Open in Web Editor NEW《动手学深度学习》习题解答,在线阅读地址如下:
Home Page: https://datawhalechina.github.io/d2l-ai-solutions-manual/
License: Other
《动手学深度学习》习题解答,在线阅读地址如下:
Home Page: https://datawhalechina.github.io/d2l-ai-solutions-manual/
License: Other
输入的x的size为[batch_size, seq_len],通过 rnn_out, _ = self.rnn(input.view(len(input), 1, -1))中的变换后送入rnn中的含义为[batch_size,1,seq_len],这里似乎是有问题的,原因在于rnn的默认的第一个维度为时间序列,不是batch_size。
放在激活函数前后应该只影响前向传播,反向传播的话,那些被置为0的神经元对应的梯度应该都是不影响的,都是0
求第九章的答案 跪谢🙇♂️
3.1.1
第一问的证明办法有点麻烦,直接对b求导,我们可以得到
然后第二问我感觉描述有点混乱,我的建议改成:
对于一个正态分布的总体,取n次样本
3.1.2
“多个局部最小值”的说法不成立,算一下Hessian可以知道解析解应该是global minimum(
练习 7.1.4这里应该占用显存和计算量大的都是后面的全连接层
来自gpt3.5的答案:
在AlexNet中,主要占用显存的部分是最后两个隐藏层,它们分别需要计算大小为64004096和40964096的矩阵,这对应于164 MB的内存占用。这两个隐藏层的计算量较大,需要进行81 MFLOPs的计算,这也是计算上的主要开销。
在计算性能方面,最后两个隐藏层需要更多的计算资源,因为它们的参数数量庞大,分别有超过4000万个参数。这导致了81 MFLOPs的计算开销,相对较高。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.