TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Build a Neural Network

174 点作者 shamdasani大约 6 年前

8 条评论

fartcannon大约 6 年前
As someone who has read a lot of implementing neural networks from articles, the massive problem with all of them is that they import numpy. You may think that it is silly to reimplement the matrix math but with out that part of the code, you can&#x27;t easily port it to other languages&#x2F;microcontrollers&#x2F;microwaves&#x2F;badgers.<p>It&#x27;s a legitimately valid part of machine learning, and its not easy to do for novices.<p>And I need help putting it on my badger damn it!
评论 #19870620 未加载
评论 #19870660 未加载
评论 #19870515 未加载
评论 #19871155 未加载
评论 #19870982 未加载
评论 #19872251 未加载
评论 #19870570 未加载
评论 #19871189 未加载
评论 #19874168 未加载
评论 #19870640 未加载
cwt137大约 6 年前
If you think this blog article is lacking, get &quot;Make Your Own Neural Network&quot; by Tariq Rashid[1]. It is way more comprehensive, but still easy to comprehend. It also uses Python to create NN from scratch.<p>1. <a href="https:&#x2F;&#x2F;www.amazon.com&#x2F;Make-Your-Own-Neural-Network&#x2F;dp&#x2F;1530826608" rel="nofollow">https:&#x2F;&#x2F;www.amazon.com&#x2F;Make-Your-Own-Neural-Network&#x2F;dp&#x2F;15308...</a>
评论 #19871017 未加载
melling大约 6 年前
Here&#x27;s another Neural Network from scratch that I found useful:<p><a href="https:&#x2F;&#x2F;victorzhou.com&#x2F;blog&#x2F;intro-to-neural-networks&#x2F;" rel="nofollow">https:&#x2F;&#x2F;victorzhou.com&#x2F;blog&#x2F;intro-to-neural-networks&#x2F;</a>
评论 #19872069 未加载
jorgeleo大约 6 年前
This tutorial explained to me at the exact level of detail:<p><a href="https:&#x2F;&#x2F;mattmazur.com&#x2F;2015&#x2F;03&#x2F;17&#x2F;a-step-by-step-backpropagation-example&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mattmazur.com&#x2F;2015&#x2F;03&#x2F;17&#x2F;a-step-by-step-backpropagat...</a><p>It was detailed enough for me to do all the calculations in an excel workbook, 1 complete cycle (forward, backward, and forward with the learned weights)<p><a href="https:&#x2F;&#x2F;1drv.ms&#x2F;x&#x2F;s!Ar06sKFtc9d7goR5WQLo-RkB0XvWAA" rel="nofollow">https:&#x2F;&#x2F;1drv.ms&#x2F;x&#x2F;s!Ar06sKFtc9d7goR5WQLo-RkB0XvWAA</a><p>Which allowed me to play with the name and factors to understand better how they impact the network as a whole.
评论 #19872123 未加载
markbnj大约 6 年前
Seems like a good intro and I plan to work through it later. I&#x27;ve been learning a lot from Michael Nielsen&#x27;s book, available at <a href="http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;index.html" rel="nofollow">http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;index.html</a>. He doesn&#x27;t shy away from the underlying math, and his appreciation for it comes through in the writing. Even without a strong math background I was able to punch through the notation and figure things out.
_jsdw大约 6 年前
In case it helps, I also had a go at an introductory neural net tutorial which I probably never shared anywhere:<p><a href="https:&#x2F;&#x2F;jsdw.me&#x2F;posts&#x2F;neural-nets&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jsdw.me&#x2F;posts&#x2F;neural-nets&#x2F;</a><p>I found that I had to read a bunch of these things to really grasp them myself.
rrggrr大约 6 年前
Would be great if this included real world data or application to understand context.
codesternews大约 6 年前
Why no biases?