Tan Sing Kuang<p>How to implement & train a fully connected autoencoder with Keras in under 100 lines of code: <a href="https://vixra.org/abs/2212.0208" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">vixra.org/abs/2212.0208</span><span class="invisible"></span></a><br /><a href="https://github.com/singkuangtan/BSautonet" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">github.com/singkuangtan/BSauto</span><span class="invisible">net</span></a><br /><a href="https://mstdn.social/tags/pythonlanguage" class="mention hashtag" rel="tag">#<span>pythonlanguage</span></a> <a href="https://mstdn.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://mstdn.social/tags/keras" class="mention hashtag" rel="tag">#<span>keras</span></a> <a href="https://mstdn.social/tags/programmingfacts" class="mention hashtag" rel="tag">#<span>programmingfacts</span></a> <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a> <a href="https://mstdn.social/tags/prototyping" class="mention hashtag" rel="tag">#<span>prototyping</span></a> :squirtle: :squirtle: :squirtle:</p>
mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.
Administered by:
Server stats:
12Kactive users
mstdn.social: About · Status · Profiles directory · Privacy policy · Terms of service
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.1
#AlgorithmsAreUs
0 posts · 0 participants · 0 posts today
Tan Sing Kuang<p>Mean Reversion Theory for trading. Let me teach you. Deep Learning, chatGPT <a href="https://www.slideshare.net/SingKuangTan/hang-seng-index-8-trends" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://www.</span><span class="ellipsis">slideshare.net/SingKuangTan/ha</span><span class="invisible">ng-seng-index-8-trends</span></a><br /><a href="https://mstdn.social/tags/meanreversion" class="mention hashtag" rel="tag">#<span>meanreversion</span></a> <a href="https://mstdn.social/tags/TradingPsychology" class="mention hashtag" rel="tag">#<span>TradingPsychology</span></a> <a href="https://mstdn.social/tags/HangSengIndex" class="mention hashtag" rel="tag">#<span>HangSengIndex</span></a> <a href="https://mstdn.social/tags/robotlife" class="mention hashtag" rel="tag">#<span>robotlife</span></a> <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/programmingfacts" class="mention hashtag" rel="tag">#<span>programmingfacts</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a></p>
Tan Sing Kuang<p>Out of different NP approximation algorithms e.g. greedy, heuristic, Tabu search, Monte Carlo, belief propagation, stochastic gradient descent, genetic algorithm, branch and bound, cutting plane... I think convex (algebraic) relaxation is the most beautiful way to solve it.<br />Deep Learning, chatGPT<br /> <a href="https://mstdn.social/tags/convexanalysis" class="mention hashtag" rel="tag">#<span>convexanalysis</span></a> <a href="https://mstdn.social/tags/optimizations" class="mention hashtag" rel="tag">#<span>optimizations</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a> <a href="https://mstdn.social/tags/programming" class="mention hashtag" rel="tag">#<span>programming</span></a> <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/geneticalgorithm" class="mention hashtag" rel="tag">#<span>geneticalgorithm</span></a> :blobcatcoffee: :blobcatcoffee: :blobcatcoffee:</p>
Tan Sing Kuang<p>ChatGPT is stupid. It is a Savant. It cannot generate new ideas, make logical inference, make mathematical formulation of a problem, optimize a problem... It can only memorized a lot of information. <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/programmingfacts" class="mention hashtag" rel="tag">#<span>programmingfacts</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a> <a href="https://mstdn.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> :pikachuroll: :pikachuroll: :pikachuroll:</p>
Tan Sing Kuang<p>Is it possible to make deep learning convex? Give me your comments <a href="https://mstdn.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a> <a href="https://mstdn.social/tags/DataScienceIsFun" class="mention hashtag" rel="tag">#<span>DataScienceIsFun</span></a> <a href="https://mstdn.social/tags/datascientists" class="mention hashtag" rel="tag">#<span>datascientists</span></a> <a href="https://mstdn.social/tags/programming" class="mention hashtag" rel="tag">#<span>programming</span></a> <a href="https://vixra.org/abs/2212.0193" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">vixra.org/abs/2212.0193</span><span class="invisible"></span></a></p>
Tan Sing Kuang<p>Can you find a denoising deep learning algorithm better than mine?? Write in the comments... :blobcatthinksmart: :blobcatthinksmart: :blobcatthinksmart: <a href="https://mstdn.social/tags/AIOverlord" class="mention hashtag" rel="tag">#<span>AIOverlord</span></a> <a href="https://mstdn.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://mstdn.social/tags/mnist" class="mention hashtag" rel="tag">#<span>mnist</span></a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#<span>AlgorithmsAreUs</span></a> <a href="https://github.com/singkuangtan/BSautonet" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">github.com/singkuangtan/BSauto</span><span class="invisible">net</span></a></p>
TrendingLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload