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。

TensorFlow.Js a painless way to get started with DeepLearning :)

16 点作者 Langhalsdino大约 7 年前

1 comment

ralusek大约 7 年前
I tried it, very painless.<p>Playing around with only a cursory understanding of neural nets, it confirmed a lot of my suspicions: the libraries have gotten good enough that a failure to understand the underlying mechanics and math can still get you like 70-80% there.<p>If you have a base understanding around concepts like &quot;activation functions,&quot; you may have gotten hung up on the precise reasoning or benefits around choosing a particular function over another. After playing around with some of the examples they&#x27;ve provided, I tried changing activation functions between sigmoid, tanh, and relu, got virtually identical results (with relu being the best). This same general pattern of seeing only marginal differences continued as I tried adding additional dense layers to the network, mostly similar results, just slower and less generalized. I tried changing filter sizes on convolutional layers for the couple image things I tried, very forgiving as well. It really felt like there is a very standardized solution to most types of problems, and the iteration that goes on to improve results is more arbitrary tweaking than it is based on any underlying theory.