Llm Fundamentals: 139 curated resources
Curated material on llm fundamentals within foundations.
139 resources · page 3 of 5
AlphaStar: Mastering the real-time strategy game StarCraft II
Creator not supplied; see original source.
Google DeepMind post on AlphaStar, the reinforcement-learning system that reached Grandmaster level in StarCraft II.
AssemblyAI engineering blog
Creator not supplied; see original source.
AssemblyAI blog with guides, model launches and voice-agent builds for speech AI.
Easy-RL / 蘑菇书
Creator not supplied; see original source.
Datawhale Easy-RL GitHub repo: Chinese reinforcement-learning tutorial (Mushroom Book) with code.
Full Stack Deep Learning
Creator not supplied; see original source.
Full Stack Deep Learning site with course materials and LLM Bootcamp lectures on building AI-powered products.
Karpathy: Unreasonable Effectiveness of RNNs
Creator not supplied; see original source.
Andrej Karpathy's 2015 essay The Unreasonable Effectiveness of Recurrent Neural Networks, with char-RNN examples.
LightGBM documentation
Creator not supplied; see original source.
LightGBM documentation: gradient boosting framework with tree-based learning, tuning guides and distributed training.
Recurrent Neural Networks and LSTM (Jürgen Schmidhuber)
Creator not supplied; see original source.
Jürgen Schmidhuber's IDSIA page on recurrent neural networks and LSTM, with history and references.
NYU Deep Learning (LeCun/Canziani)
Creator not supplied; see original source.
NYU Deep Learning course (Spring 2021) by Yann LeCun and Alfredo Canziani, with lectures, labs and notebooks.
OECD AI Recommendation (OECD-LEGAL-0449)
Creator not supplied; see original source.
OECD Recommendation of the Council on Artificial Intelligence, the source of the OECD AI Principles and AI system definition.
PDE-Transformer
Creator not supplied; see original source.
PDE-Transformer project page: transformer architecture for learning partial differential equations from data.
Physics-based Deep Learning (TUM)
Creator not supplied; see original source.
Physics-based Deep Learning book from TUM: hands-on guide to combining physical simulation with deep learning.
PointNet
Creator not supplied; see original source.
PointNet project page: deep network architecture that consumes raw point clouds for 3D classification and segmentation.
Roboflow documentation
Creator not supplied; see original source.
Roboflow documentation for building computer-vision datasets, training models and deploying them.
sktime
Creator not supplied; see original source.
sktime: open-source Python framework for time-series forecasting, classification and anomaly detection.
Soniox Docs: Models
Creator not supplied; see original source.
Soniox models page listing speech-to-text model versions, changelog and deprecations.
Speechmatics technical articles
Creator not supplied; see original source.
Speechmatics articles on speech recognition technology, product news and AI research.
UvA Deep Learning tutorials
Creator not supplied; see original source.
University of Amsterdam deep learning tutorial notebooks in PyTorch and JAX/Flax, covering core architectures.
XGBoost documentation
Creator not supplied; see original source.
XGBoost documentation: distributed gradient boosting library with training, GPU support and parameter guides.
YSDA Practical Deep Learning
Creator not supplied; see original source.
YSDA Practical_DL GitHub repo: deep learning course materials from Yandex School of Data Analysis, HSE and Skoltech.
YSDA Practical RL
Creator not supplied; see original source.
YSDA Practical_RL GitHub repo: open reinforcement-learning course with notebooks and assignments from HSE and YSDA.
Zoom Scribe API documentation
Creator not supplied; see original source.
Zoom Scribe API documentation: transcription service for many media formats, with modes and authentication details.
Agent57
Creator not supplied; see original source.
arXiv paper (2020) introducing Agent57, the first agent to exceed the human baseline on all 57 Atari games.
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
Creator not supplied; see original source.
NeurIPS paper (PDF, 2012) AlexNet: ImageNet classification with deep convolutional neural networks.
Faster sorting algorithms discovered using deep reinforcement learning (AlphaDev)
Creator not supplied; see original source.
Nature paper (2023) on AlphaDev discovering faster sorting algorithms with deep RL.
Mastering the game of Go with deep neural networks and tree search (AlphaGo)
Creator not supplied; see original source.
Nature paper (2016) on AlphaGo, mastering Go with deep neural networks and tree search.
Grandmaster level in StarCraft II using multi-agent reinforcement learning (AlphaStar)
Creator not supplied; see original source.
Nature paper (2019) on AlphaStar reaching grandmaster level in StarCraft II with multi-agent RL.
Discovering faster matrix multiplication algorithms with reinforcement learning (AlphaTensor)
Creator not supplied; see original source.
Nature paper (2022) on AlphaTensor discovering faster matrix multiplication algorithms with RL.
AlphaZero
Creator not supplied; see original source.
arXiv paper (2017) introducing AlphaZero, mastering chess and shogi through self-play reinforcement learning.
Chronos: Learning the Language of Time Series
Creator not supplied; see original source.
arXiv paper (2024) introducing Chronos, pretrained time-series forecasting models using language-model tokenization.
CLIP
Creator not supplied; see original source.
arXiv paper (2021) introducing CLIP, contrastive language-image pretraining for transferable visual models.
DenseNet
Creator not supplied; see original source.
arXiv paper (2016) "Densely Connected Convolutional Networks", introducing DenseNet, where each layer receives feature maps from all earlier layers.
DETR
Creator not supplied; see original source.
arXiv HTML version of the DETR paper (2020) on end-to-end object detection with transformers.