TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Differentiable Programming

86 pointsby efmover 9 years ago

5 comments

subnaughtover 9 years ago
This seems to be heavily influenced by (if not outright plagiarized from) this[0], which, needless to say, does a much more thorough job of explaining things.<p>[0]: <a href="http:&#x2F;&#x2F;colah.github.io&#x2F;posts&#x2F;2015-09-NN-Types-FP&#x2F;" rel="nofollow">http:&#x2F;&#x2F;colah.github.io&#x2F;posts&#x2F;2015-09-NN-Types-FP&#x2F;</a>
评论 #10829140 未加载
评论 #10829118 未加载
评论 #10829025 未加载
评论 #10828750 未加载
im2w1lover 9 years ago
I previously made a toy VM where a program consisted of a matrix, rows corresponded to instruction slot, and then the values in that row were probabilities for different instructions. This means probability of emitting a specific output is differentiable in the probabilities, which can then be learned.<p>Didn&#x27;t get very good results though.
评论 #10832588 未加载
thomasahleover 9 years ago
So what&#x27;s up with that differentiable stack? Is that similar to what the Facebook people were doing on learning addition?
评论 #10828914 未加载
评论 #10829356 未加载
tluyben2over 9 years ago
Some code on the subject:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;zenna&#x2F;Arrows.jl" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;zenna&#x2F;Arrows.jl</a> <a href="https:&#x2F;&#x2F;github.com&#x2F;wojzaremba&#x2F;algorithm-learning" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;wojzaremba&#x2F;algorithm-learning</a>
dnauticsover 9 years ago
&gt; This newly dominant approach, originally known as &quot;neural networks,&quot; is now branded &quot;deep learning,&quot;<p>Is this true? My impression is that &quot;deep learning&quot; is a series of mathematical tricks and design and implementation concepts that get you to solve neural networks of depth greater than 3-4, which becomes mathematically challenging.
评论 #10829798 未加载