toad.social

Nom__XD, 飲ん,诺穆 (They/Them)🐈‍⬛<a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://mastodon.social/tags/chatgpt" class="mention hashtag" rel="nofollow noopener" target="_blank">#chatgpt</a> <a href="https://mastodon.social/tags/claude" class="mention hashtag" rel="nofollow noopener" target="_blank">#claude</a> <a href="https://mastodon.social/tags/gemini" class="mention hashtag" rel="nofollow noopener" target="_blank">#gemini</a> <a href="https://mastodon.social/tags/grok" class="mention hashtag" rel="nofollow noopener" target="_blank">#grok</a> <a href="https://mastodon.social/tags/deepseek" class="mention hashtag" rel="nofollow noopener" target="_blank">#deepseek</a> <a href="https://mastodon.social/tags/alexa" class="mention hashtag" rel="nofollow noopener" target="_blank">#alexa</a> <a href="https://mastodon.social/tags/copilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#copilot</a> <a href="https://mastodon.social/tags/vibecoding" class="mention hashtag" rel="nofollow noopener" target="_blank">#vibecoding</a> <a href="https://mastodon.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a> <a href="https://mastodon.social/tags/behaviortrees" class="mention hashtag" rel="nofollow noopener" target="_blank">#behaviortrees</a> <a href="https://mastodon.social/tags/cnns" class="mention hashtag" rel="nofollow noopener" target="_blank">#cnns</a> <a href="https://mastodon.social/tags/transfomers" class="mention hashtag" rel="nofollow noopener" target="_blank">#transfomers</a> <a href="https://mastodon.social/tags/dnns" class="mention hashtag" rel="nofollow noopener" target="_blank">#dnns</a> <a href="https://mastodon.social/tags/supervisedlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#supervisedlearning</a> <a href="https://mastodon.social/tags/unsupervisedlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#unsupervisedlearning</a> <a href="https://mastodon.social/tags/reinforcedlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#reinforcedlearning</a> <a href="https://mastodon.social/tags/aiart" class="mention hashtag" rel="nofollow noopener" target="_blank">#aiart</a> <a href="https://mastodon.social/tags/ArtificialInteligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#ArtificialInteligence</a> <a href="https://mastodon.social/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#nlp</a> 🖕🐾

Annual Computer Security Applications ConferenceEnding the session, we saw Park et al.'s "DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks" demonstrating the detection of unlawful dataset use in <a href="https://infosec.exchange/tags/DNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#DNNs</a>. (<a href="https://www.acsac.org/2023/program/final/s321.html" rel="nofollow noopener" translate="no" target="_blank">https://www.acsac.org/2023/program/final/s321.html</a>) 4/4 <a href="https://infosec.exchange/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#DeepLearning</a> <a href="https://infosec.exchange/tags/DataSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataSecurity</a>

Christos Argyropoulos MD, PhDCompressors such as <a href="https://mstdn.science/tags/gzip" class="mention hashtag" rel="nofollow noopener" target="_blank">#gzip</a> + <a href="https://mstdn.science/tags/kNN" class="mention hashtag" rel="nofollow noopener" target="_blank">#kNN</a> (k-nearest-neighbor i.e. your grandparents' <a href="https://mstdn.science/tags/classifier" class="mention hashtag" rel="nofollow noopener" target="_blank">#classifier</a>) beats the living daylights of Deep neural networks (<a href="https://mstdn.science/tags/DNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#DNNs</a>) in sentence classification. H/t <a href="https://lingo.lol/@lgessler" class="u-url mention" rel="nofollow noopener" target="_blank">@lgessler</a> Without any training parameters, this non-parametric, easy and lightweight (no <a href="https://mstdn.science/tags/GPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#GPU</a>) method achieves results that are competitive with non-pretrained deep learning methods on six in-distribution datasets.It even outperforms BERT on all five OOD datasets.<a href="https://mstdn.science/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://mstdn.science/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> <a href="https://aclanthology.org/2023.findings-acl.426/" rel="nofollow noopener" target="_blank">https://aclanthology.org/2023.findings-acl.426/</a>

Nick Byrd, Ph.D.Why <a href="https://nerdculture.de/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#DeepNeuralNetworks</a> need <a href="https://nerdculture.de/tags/Logic" class="mention hashtag" rel="nofollow noopener" target="_blank">#Logic</a>:Nick Shea (<a href="https://nerdculture.de/tags/UCL" class="mention hashtag" rel="nofollow noopener" target="_blank">#UCL</a>/#Oxford) suggests(1) Generating novel stuff (e.g., <a href="https://nerdculture.de/tags/Dalle" class="mention hashtag" rel="nofollow noopener" target="_blank">#Dalle</a>'s art, <a href="https://nerdculture.de/tags/GPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#GPT</a>'s writing) is cool, but slow and inconsistent.(2) Just a handful of logical inferences can be used *across* loads of situations (e.g., <a href="https://nerdculture.de/tags/modusPonens" class="mention hashtag" rel="nofollow noopener" target="_blank">#modusPonens</a> works the same way every time).So (3) by <a href="https://nerdculture.de/tags/learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#learning</a> Logic, <a href="https://nerdculture.de/tags/DNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#DNNs</a> would be able to recycle a few logical moves on a MASSIVE number of problems (rather than generate a novel solution from scratch for each one).<a href="https://nerdculture.de/tags/CompSci" class="mention hashtag" rel="nofollow noopener" target="_blank">#CompSci</a> <a href="https://nerdculture.de/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a>

Recent searches

Search options

Administered by:

Server stats:

#dnns