Discover the Best AI Resources
Curated essentials, no noise — just what matters
AI Others2015
Curated collection of AI courses, books, video lectures, papers and engineering guides for developers building generative models and agentic systems. Actively maintained with a weekly, evidence-backed curation workflow and an opinionated quality bar.
AI Train2015
End-to-end quantitative trading framework that covers feature engineering, model training, signal generation and live execution; includes vnpy.alpha for ML-driven strategy research and workflow management, aimed at production trading and research pipelines.
Karpathy's 2015 walkthrough of character-level RNNs trained to predict the next character, showing how a tiny model learns to generate convincing Shakespeare, C code, and LaTeX — and what its neurons actually track.
Repurposes attention as a pointer that selects positions in the input rather than blending them into a context vector, so the output vocabulary can grow with input length — handling sorting, convex hulls, and TSP that fixed seq2seq cannot.
Walks through the LSTM gating mechanism step by step, showing how the cell state and forget/input/output gates let the network carry information across long sequences where plain RNNs lose it to vanishing gradients.
AI Infra2015
Exposes auto-generated REST and GraphQL APIs from visual content models so teams can self-host a headless CMS and manage content via a customizable admin UI. Provides a plugin system, TypeScript support, multiple database options, and optional Strapi Cloud hosting.
AI Infra2015
Builds and deploys machine learning models across research, production, web, mobile, and edge environments. Its ecosystem spans Keras, TFX, LiteRT, TensorFlow.js, datasets, model hubs, and visualization tools.
Demonstrates that the order you feed inputs and outputs into a seq2seq model changes what it learns — even for sets that have no inherent order — and adds an attention-based set encoder plus a training loss that searches over output orderings.
Introduced dilated (atrous) convolutions, which expand a filter's receptive field exponentially with no loss of resolution and no extra parameters — the trick that let dense-prediction networks see wide context while keeping per-pixel detail.
Bet that one neural net, scaled with HPC, could transcribe both English and Mandarin without hand-built pipelines — reaching human-competitive accuracy by training fast enough to iterate on architecture in days, not weeks.
Before residual connections, stacking more layers made networks worse, not better — this 2015 paper fixed that by having layers learn a residual F(x)=H(x)-x via shortcut connections, enabling 152-layer nets that won ILSVRC 2015.
Combines a policy network (to narrow move choices) and a value network (to score board positions) with Monte Carlo tree search, cutting Go's vast search space enough to beat top programs 99.8% of the time and the European champion 5-0.