Don LimWhat is 1-bit LLM? — Bitnet.cpp may eliminate GPUsMicrosoft introduces Bitnet.cpp, a lightweight AI model that can run efficiently on a portable device.Oct 19, 20244954Oct 19, 20244954
DevanshKolmogorov–Arnold Networks: Hype or Deep Learning Revolution?Will the better interpretability, smaller network sizes, and learnable activations allow KANs to topple MLPsJun 16, 20242354Jun 16, 20242354
Ignacio de GregorioYOCO, A New Foundation Model to Eliminate Transformers?You Only Cache OnceJun 2, 20241.5K13Jun 2, 20241.5K13
Isaak KamauA Simplified Explanation Of The New Kolmogorov-Arnold Network (KAN) from MITA screenshot from: https://arxiv.org/abs/2404.19756May 1, 20243.4K8May 1, 20243.4K8
InTDS ArchivebyFabio SigristDemystifying ROC and precision-recall curvesDebunking some myths about the ROC curve / AUC and the precision-recall curve / AUPRC for binary classification with a focus on imbalanced…Jan 25, 20221944Jan 25, 20221944
InTDS ArchivebyArjun SarkarBuild your own Transformer from scratch using PytorchBuilding a Transformer model step by step in PytorchApr 26, 202377914Apr 26, 202377914
Martin ThissenUnderstanding and Coding the Attention Mechanism — The Magic Behind TransformersIn this article, I’ll give you an introduction to the attention mechanism and show you how to code the attention mechanism yourself.Dec 6, 20222662Dec 6, 20222662
InTDS ArchivebyNeeraj KrishnaIntroduction to p-value and Significance Testing with ExamplesUnderstand the idea behind the hypothesis testing framework through examplesJan 18, 20231811Jan 18, 20231811
Theo WolfPhysics-informed Neural Networks: a simple tutorial with PyTorchMake your neural networks better in low-data regimes by regularising with differential equationsApr 13, 20233504Apr 13, 20233504
InTowards AIbyAli MoezziThe Complete Guide to Spiking Neural NetworksEverything you need to know about Spiking Neural Networks from architecture, temporal behavior, encoding to neuromorphic hardwareApr 4, 20234013Apr 4, 20234013
InSyncedReviewbySyncedIntroducing SpikeGPT: UCSC & Kuaishou’s LLM With Spiking Neural Networks Slashes Language…While the power and performance of today’s large language models (LLMs) are beyond anything previously seen from AI, so too are their…Mar 7, 2023401Mar 7, 2023401
InBetter ProgrammingbyLev MaximovEinsum VisualizedA Swiss army knife of the array multiplicationMar 1, 20231653Mar 1, 20231653
InTDS ArchivebyMichael GalkinNeural Graph DatabasesA new milestone in graph data managementMar 28, 20237133Mar 28, 20237133
InGeek CulturebyAbhinavHow to Download a Scientific Paper for FreeEverything you need to knowOct 2, 20224016Oct 2, 20224016
InTDS ArchivebyRafael Bischof4 Ideas for Physics-Informed Neural Networks that failedHere is a list of extensions for PINNs that either did not improve their performance, or broke them completely — so you do not have to try…Feb 11, 2023652Feb 11, 2023652
InTDS ArchivebyLukáš ZahradníkBeyond Transformers with PyNeuraLogicBeyond standard transformers with a neuro-symbolic AI frameworkFeb 7, 20232651Feb 7, 20232651
InTDS ArchivebySamuele MazzantiData Scientists Need to Know Just One Statistical TestAfter you read this, you will be able to test any possible statistical hypothesis. With a unique algorithm.Jun 30, 20221.4K21Jun 30, 20221.4K21
Bogumił KamińskiThe Zen of Missing in JuliaSome time ago I have written a post about ABC of handling missing values in Julia. Its objective was to give an introduction to the topic…Jun 17, 202235Jun 17, 202235
Joseph GardiA Visual Introduction to Einstein Notation and why you should Learn Tensor CalculusTensors are differential equations are polynomialsMay 13, 20221193May 13, 20221193
InTowards AIbyMarie Stephen LeoNo Training Data? No Problem! Weak Supervision to the Rescue!Use domain knowledge to generate large labeled datasets with state-of-the-art NLP Weak Supervision.May 17, 20221661May 17, 20221661