Mastodon 🐘

0 posts0 participants0 posts today

IT NewsGoing Digital: Teaching a TI-84 Handwriting Recognition - You wouldn’t typically associate graphing calculators with artificial intelligence... - <a href="https://hackaday.com/2024/12/24/going-digital-teaching-a-ti-84-handwriting-recognition/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://hackaday.com/2024/12/24/going-digital-teaching-a-ti-84-handwriting-recognition/</a> <a href="https://schleuss.online/tags/convolutionalneuralnetwork" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#convolutionalneuralnetwork</a> <a href="https://schleuss.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#artificialintelligence</a> <a href="https://schleuss.online/tags/graphicscalculator" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#graphicscalculator</a> <a href="https://schleuss.online/tags/texasinstruments" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#texasinstruments</a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#machinelearning</a> <a href="https://schleuss.online/tags/handheldshacks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#handheldshacks</a> <a href="https://schleuss.online/tags/neuralnetwork" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#neuralnetwork</a> <a href="https://schleuss.online/tags/handwriting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#handwriting</a> <a href="https://schleuss.online/tags/ti" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ti</a>-84plusce <a href="https://schleuss.online/tags/calculator" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#calculator</a> <a href="https://schleuss.online/tags/mnist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mnist</a> <a href="https://schleuss.online/tags/ti" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ti</a>-84 <a href="https://schleuss.online/tags/news" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#news</a>

Habr[Перевод] Нейронные сети (инференс MNIST) на «3-центовом» микроконтроллереВдохновившись на удивление высокой производительностью нейронных сетей и обучением с учётом квантования на микроконтроллере CH32V003 , я захотел выяснить, как далеко эту идею можно развить. Насколько можно сжать нейронную сеть с сохранением высокой точности тестов на датасете MNIST? Когда речь идёт о крайне дешёвых микроконтроллерах, сложно предположить что-то более подходящее, чем 8-битные Padauk . Эти устройства оптимизированы под простейшие и самые дешёвые приложения из доступных. Самая мелкая модель серии, PMS150C, оснащена однократно программируемой памятью в 1024 13-битных слова и 64 байтами RAM — на порядок меньше, чем в CH32V003. Кроме того, эта модель в противоположность намного более мощному набору инструкций RISC-V содержит коммерческий регистр-аккумулятор на основе 8-битной архитектуры. Возможно ли реализовать механизм инференса MNIST, способный классифицировать рукописные числа, также и на PMS150C?<a href="https://habr.com/ru/companies/ruvds/articles/853050/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/companies/ruvds/articles/853050/</a><a href="https://zhub.link/tags/ruvds_%D0%BF%D0%B5%D1%80%D0%B5%D0%B2%D0%BE%D0%B4" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ruvds_перевод</a> <a href="https://zhub.link/tags/%D0%BC%D0%B0%D1%88%D0%B8%D0%BD%D0%BD%D0%BE%D0%B5_%D0%BE%D0%B1%D1%83%D1%87%D0%B5%D0%BD%D0%B8%D0%B5" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#машинное_обучение</a> <a href="https://zhub.link/tags/%D0%BC%D0%B8%D0%BA%D1%80%D0%BE%D0%BA%D0%BE%D0%BD%D1%82%D1%80%D0%BE%D0%BB%D0%BB%D0%B5%D1%80%D1%8B" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#микроконтроллеры</a> <a href="https://zhub.link/tags/PMS150C" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#PMS150C</a> <a href="https://zhub.link/tags/mnist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mnist</a> <a href="https://zhub.link/tags/CH32V003" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#CH32V003</a>

HabrMojo: убийца Python и будущее Ai?Всем привет! Меня зовут Вадим, я Data Scientist в компании Raft, и сегодня мы погрузимся в Mojo. Я уже делал обзор данного языка программирования и рассмотрел его преимущества, примеры использования, а также провел сравнение с Python. Теперь давайте посмотрим, как обучить простую сверточную нейронную сеть, и разберём один из методов машинного обучения — линейную регрессию. В качестве примеров задач возьмем стандартные соревнования машинного обучения: предсказание стоимости жилья и классификацию рукописных цифр MNIST. Для проведения экспериментов на Python используем фреймворк машинного обучения PyTorch. А на Mojo — фреймворк машинного обучения Basalt.<a href="https://habr.com/ru/companies/oleg-bunin/articles/843044/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/companies/oleg-bunin/articles/843044/</a><a href="https://zhub.link/tags/mojo" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mojo</a> <a href="https://zhub.link/tags/%D0%BC%D0%B0%D1%88%D0%B8%D0%BD%D0%BD%D0%BE%D0%B5" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#машинное</a>+обучение <a href="https://zhub.link/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#python</a> <a href="https://zhub.link/tags/%D0%B8%D1%81%D0%BA%D1%83%D1%81%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B8%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#искусственный_интеллект</a> <a href="https://zhub.link/tags/%D0%BD%D0%B5%D0%B9%D1%80%D0%BE%D1%81%D0%B5%D1%82%D0%B8" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#нейросети</a> <a href="https://zhub.link/tags/%D0%BF%D1%80%D0%BE%D0%B3%D1%80%D0%B0%D0%BC%D0%BC%D0%B8%D1%80%D0%BE%D0%B2%D0%B0%D0%BD%D0%B8%D0%B5" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#программирование</a> <a href="https://zhub.link/tags/mnist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mnist</a> <a href="https://zhub.link/tags/pytorch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#pytorch</a> <a href="https://zhub.link/tags/basalt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#basalt</a> <a href="https://zhub.link/tags/Housing_Prices_Dataset" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Housing_Prices_Dataset</a>

:rss: Qiita - 人気の記事ED法でmnistを学習する(BCELoss) <a href="https://qiita.com/malt03/items/ad8eae77c46496e304c2?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://qiita.com/malt03/items/ad8eae77c46496e304c2?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items</a><a href="https://rss-mstdn.studiofreesia.com/tags/qiita" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#qiita</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Rust" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Rust</a> <a href="https://rss-mstdn.studiofreesia.com/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> <a href="https://rss-mstdn.studiofreesia.com/tags/ED%E6%B3%95" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ED法</a>

Steve Leach<a href="https://sigmoid.social/@lowd" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@lowd</a> I remember when most ML applications were variations on <a href="https://sigmoid.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a>. And <a href="https://sigmoid.social/tags/Imagenet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Imagenet</a>, but I only had enough computer at the time to play around with Mnist. But yea, even then "Recommendation Engines" were starting to be the first things anyone mentioned because it was low hanging fruit - something of immediately obvious commercial value with terrific training data and an easy task for deployment.

Fabrizio MusacchioThe <a href="https://sigmoid.social/tags/Wasserstein" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Wasserstein</a> <a href="https://sigmoid.social/tags/metric" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#metric</a> (<a href="https://sigmoid.social/tags/EMD" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#EMD</a>) can be used, to train <a href="https://sigmoid.social/tags/GenerativeAdversarialNetworks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#GenerativeAdversarialNetworks</a> (<a href="https://sigmoid.social/tags/GANs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#GANs</a>) more effectively. This tutorial compares a default GAN with a <a href="https://sigmoid.social/tags/WassersteinGAN" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#WassersteinGAN</a> (<a href="https://sigmoid.social/tags/WGAN" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#WGAN</a>) trained on the <a href="https://sigmoid.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> dataset.🌎 <a href="https://www.fabriziomusacchio.com/blog/2023-07-29-wgan/" rel="nofollow noopener noreferrer" target="_blank">https://www.fabriziomusacchio.com/blog/2023-07-29-wgan/</a><a href="https://sigmoid.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MachineLearning</a>

ai-Paul EI experimented with using Large Language Models to solve a complex <a href="https://sigmoid.social/tags/imagerecognition" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#imagerecognition</a> problem. The generated machine learning model by ChatGPT using a few prompts was able to detect <a href="https://sigmoid.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> handwritten digits with an accuracy of 98%.Read on if you want to learn how I did this.<a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AI</a> <a href="https://sigmoid.social/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#artificialintelligence</a> <a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#deeplearning</a> <a href="https://sigmoid.social/tags/neuralnetworks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#neuralnetworks</a> <a href="https://sigmoid.social/tags/bingai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#bingai</a> <a href="https://sigmoid.social/tags/bingchat" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#bingchat</a> <a href="https://sigmoid.social/tags/convolutionalneuralnetworks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#convolutionalneuralnetworks</a> <a href="https://sigmoid.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#LLMs</a> <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#computervision</a> <a href="https://blog.gopenai.com/using-chatgpt-to-solve-the-mnist-image-recognition-problem-with-deep-learning-ai-796153d80193" rel="nofollow noopener noreferrer" target="_blank">https://blog.gopenai.com/using-chatgpt-to-solve-the-mnist-image-recognition-problem-with-deep-learning-ai-796153d80193</a>

ai-Paul EUsing ChatGPT to solve the MNIST Image Recognition Problem with Deep Learning AI <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#computervision</a> <a href="https://sigmoid.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChatGPT</a> <a href="https://sigmoid.social/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#OpenAI</a> <a href="https://sigmoid.social/tags/NeuralNetworks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#NeuralNetworks</a> <a href="https://sigmoid.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> <a href="https://sigmoid.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#PromptEngineering</a> <a href="https://sigmoid.social/tags/ImageRecognition" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ImageRecognition</a> <a href="https://sigmoid.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#DeepLearning</a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AI</a> <a href="https://www.linkedin.com/pulse/using-chatgpt-solve-mnist-image-recognition-problem-deep-paul-ekwere?utm_source=share&utm_medium=member_android&utm_campaign=share_via" rel="nofollow noopener noreferrer" target="_blank">https://www.linkedin.com/pulse/using-chatgpt-solve-mnist-image-recognition-problem-deep-paul-ekwere?utm_source=share&utm_medium=member_android&utm_campaign=share_via</a>

Oliver Sampson<a href="https://mastodon.social/@Sardonicus" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@Sardonicus</a> I d love to know how <a href="https://sigmoid.social/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ml</a> algorithms trained on the <a href="https://sigmoid.social/tags/mnist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mnist</a> dataset would perform with those images.

antonio vergariIt's hard to assess <a href="https://ellis.social/tags/Continual" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Continual</a> <a href="https://ellis.social/tags/Learning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Learning</a> models and disentangle <a href="https://ellis.social/tags/hype" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#hype</a> from <a href="https://ellis.social/tags/progress" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#progress</a>, as the eval landscape is fragmented.Even when learning from <a href="https://ellis.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> to tiny <a href="https://ellis.social/tags/ImageNet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ImageNet</a> (and back) <a href="https://ellis.social/tags/sota" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#sota</a> models tend to <a href="https://ellis.social/tags/catastrophic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#catastrophic</a> <a href="https://ellis.social/tags/forget" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#forget</a> a lot!cc @ContinualAI👉<a href="https://arxiv.org/abs/2303.11076" rel="nofollow noopener noreferrer" target="_blank">https://arxiv.org/abs/2303.11076</a>

JuliuMicrograd is very simple, only fully connected layers. So first trying to find out if it can even learn numbers based on MNIST dataset.Then I hope to at least be able to verfit, so the essence works. Then I'll have the challenge of trying to make it work for every icon in the app.Presumably I have to create/generate a huge set of icon images to train on..<a href="https://indieweb.social/tags/ux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ux</a> <a href="https://indieweb.social/tags/micrograd" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#micrograd</a> <a href="https://indieweb.social/tags/reactNative" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#reactNative</a> <a href="https://indieweb.social/tags/MLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MLP</a> <a href="https://indieweb.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> <a href="https://indieweb.social/tags/TinyUX" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#TinyUX</a> <a href="https://indieweb.social/tags/Karpathy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Karpathy</a> <a href="https://indieweb.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://indieweb.social/tags/NeuralNet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#NeuralNet</a>

Tan Sing KuangCan 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">#AIOverlord</a> <a href="https://mstdn.social/tags/deeplearning" class="mention hashtag" rel="tag">#deeplearning</a> <a href="https://mstdn.social/tags/mnist" class="mention hashtag" rel="tag">#mnist</a> <a href="https://mstdn.social/tags/AlgorithmsAreUs" class="mention hashtag" rel="tag">#AlgorithmsAreUs</a> <a href="https://github.com/singkuangtan/BSautonet" target="_blank" rel="nofollow noopener noreferrer" translate="no">https://github.com/singkuangtan/BSautonet</a>

RecursiveNeuron :verified:Deep learning series: Project setup (CNN for MNIST)<a href="https://youtu.be/2JkJZQP9dHg" rel="nofollow noopener noreferrer" target="_blank">https://youtu.be/2JkJZQP9dHg</a><a href="https://techhub.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#DeepLearning</a> <a href="https://techhub.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MachineLearning</a> <a href="https://techhub.social/tags/artificalintelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#artificalintelligence</a> <a href="https://techhub.social/tags/mnist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#mnist</a>

Jane AdamsNothing like the <a href="https://vis.social/tags/Kaggle" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Kaggle</a> <a href="https://vis.social/tags/fashion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#fashion</a> <a href="https://vis.social/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a> variant to make me feel like a real Elle Woods over here doing t-SNE on purses and saliency maps on ankle boots 😅 <a href="https://github.com/janeadams/fashion_model_analysis/" rel="nofollow noopener noreferrer" target="_blank">https://github.com/janeadams/fashion_model_analysis/</a><a href="https://vis.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MachineLearning</a> <a href="https://vis.social/tags/WomeninSTEM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#WomeninSTEM</a> <a href="https://vis.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AI</a> <a href="https://vis.social/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ML</a> <a href="https://vis.social/tags/tsne" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#tsne</a> <a href="https://vis.social/tags/pca" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#pca</a> <a href="https://vis.social/tags/WiDS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#WiDS</a> <a href="https://vis.social/tags/Python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Python</a>

Albert Cardona<a href="https://qoto.org/@ilennaj" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@ilennaj</a> And you are the author of this most spectacular arXiv paper: "Can single neurons solve MNIST? the computational power of biological dendritic trees" Jones & Kording 2020 <a href="https://arxiv.org/abs/2009.01269" rel="nofollow noopener noreferrer" target="_blank">https://arxiv.org/abs/2009.01269</a> Hats off to you & <a href="https://sigmoid.social/@kordinglab" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@kordinglab</a> ! And welcome.<a href="https://qoto.org/tags/neuroscience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#neuroscience</a> <a href="https://qoto.org/tags/dendrites" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#dendrites</a> <a href="https://qoto.org/tags/MNIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#MNIST</a>PS: subsequently published as "Might a Single Neuron Solve Interesting Machine Learning Problems Through Successive Computations on Its Dendritic Tree?" Jones & Kording 2021 <a href="https://direct.mit.edu/neco/article/33/6/1554/100576/Might-a-Single-Neuron-Solve-Interesting-Machine" rel="nofollow noopener noreferrer" target="_blank">https://direct.mit.edu/neco/article/33/6/1554/100576/Might-a-Single-Neuron-Solve-Interesting-Machine</a>

Recent searches

Search options

Administered by:

Server stats:

#mnist