InAI AdvancesbyWei-Meng LeeUnderstanding Model DistillationLearn what model distillation is and how it works by building one yourselfFeb 16Feb 16
AI Papers AcademyMixture of Nested Experts | AI Paper ExplainedIn this post we dive into Mixture of Nested Experts, a new method presented by Google that can dramatically reduce AI computational costAug 12, 2024Aug 12, 2024
InTDS ArchivebyMengliu ZhaoA Practical Guide to Contrastive LearningHow to build your very first SimSiam model with FashionMNISTJul 30, 2024Jul 30, 2024
Hamdi BoukamchaFine-Tuning a ResNet18 Model with Optuna: Hyperparameter OptimizationDeep learning models are powerful tools, but achieving optimal performance requires careful tuning of hyperparameters. This task can be…Aug 12, 2024Aug 12, 2024
Sik-Ho TsangBrief Review — Improved Knowledge Distillation via Teacher AssistantTeacher Assistant Knowledge Distillation (TAKD)Aug 6, 2024Aug 6, 2024
InTowards AIbyIgor NovikovRAG Architecture: Advanced RAGSince the writing of my last article, not much time has passed, but progress doesn’t stand still, and several important changes have…Jul 22, 20241Jul 22, 20241
InTDS ArchivebyMaarten GrootendorstA Visual Guide to QuantizationDemystifying the compression of large language modelsJul 24, 20243Jul 24, 20243
InTDS ArchivebyHesam SheikhUnderstanding Kolmogorov–Arnold Networks (KAN)Why KANs are a potential alternative to MPLs and the current landscape of Machine Learning. Let’s go through the paper to find out.May 7, 20242May 7, 20242
InTDS ArchivebyNate CibikQuantizing the AI ColossiStreamlining Giants Part 2: Neural Network QuantizationApr 15, 2024Apr 15, 2024
Astarag MohapatraMAMBA and State Space Models ExplainedThis article will go through a new class of deep learning models called Structured State Spaces and Mamba.Feb 1, 20241Feb 1, 20241
InTDS ArchivebyMaxime LabonneCreate Mixtures of Experts with MergeKitCombine multiple models into a single MoEMar 27, 20247Mar 27, 20247
InArtificial Intelligence in Plain EnglishbyAbdulkader HelwanLoRA: The Magical Finetuning ToolWhat is LoRA and How Does it Work?Mar 11, 2024Mar 11, 2024
InSelf-Supervised LearningbyFrederik vom LehnContrastive Learning Loss: NT-Xent & InfoNCEAug 20, 2023Aug 20, 2023
InTDS ArchivebySheila TeoStacked Ensembles for Advanced Predictive Modeling With H2O.ai and OptunaAnd how I placed top 10% in Europe’s largest machine learning competition with them!Dec 18, 20238Dec 18, 20238
WillReview — What do self-supervised Vision Transformer Learn?When attempting Self-supervised Learning, there are two main methods: Contrastive Learning (CL) and Masked Image Modeling (MIM). However…Oct 2, 2023Oct 2, 2023
InAIGuysbyVishal RajputXGBoost 2.0: Major update on Tree-based methodsXGBoost still rules the domain of tabular dataOct 6, 202311Oct 6, 202311
InArtificial Intelligence in Plain EnglishbySik-Ho TsangBrief Review — Divide and Contrast: Self-supervised Learning from Uncurated DataA New Baseline MoCLR Established, DnC Further Improves MoCLROct 2, 2023Oct 2, 2023
InTDS ArchivebyMariano KampDive Into LoRA AdaptersExploring Parameter Efficient Finetuning (PEFT): Intuitively Understanding Finetuning Using LoRAAug 25, 20235Aug 25, 20235
InTDS ArchivebyRiccardo AndreoniEnsemble Learning with Scikit-Learn: A Friendly IntroductionEnsemble learning algorithms like XGBoost or Random Forests are among the top-performing models in Kaggle competitions. How do they work?Sep 9, 20231Sep 9, 20231
Nikolaos GiakoumoglouPySSL : Self-Supervised Learning being easy again!IntroductionJun 19, 20232Jun 19, 20232
