diff --git a/our-initiatives/tutorials/2024-2025/_category_.json b/our-initiatives/tutorials/2024-2025/_category_.json index 3438085..69f726b 100644 --- a/our-initiatives/tutorials/2024-2025/_category_.json +++ b/our-initiatives/tutorials/2024-2025/_category_.json @@ -5,4 +5,4 @@ "type": "doc", "id": "tutorials/2024-2025/index" } -} +} \ No newline at end of file diff --git a/our-initiatives/tutorials/2025-2026/_category_.json b/our-initiatives/tutorials/2025-2026/_category_.json new file mode 100644 index 0000000..5668a2a --- /dev/null +++ b/our-initiatives/tutorials/2025-2026/_category_.json @@ -0,0 +1,8 @@ +{ + "label": "2025-2026", + "position": 2, + "link": { + "type": "doc", + "id": "tutorials/2025-2026/index" + } +} \ No newline at end of file diff --git a/our-initiatives/tutorials/2025-2026/index.mdx b/our-initiatives/tutorials/2025-2026/index.mdx new file mode 100644 index 0000000..0b0704b --- /dev/null +++ b/our-initiatives/tutorials/2025-2026/index.mdx @@ -0,0 +1,69 @@ +--- +sidebar_position: 1 +--- + +import DocCardList from '@theme/DocCardList' + +# 💻 Machine Learning Tutorial Series + +Welcome to season 4 (2024-25) of the beginner machine learning tutorial series of the UCL Artificial Intelligence Society! + +If you have any questions about our content or machine learning more generally, feel free to ask us at the next session or make a forum post on the [UCLAIS Discord server](https://discord.gg/KSUZuQx?ltclid=3f704b3b-9044-415a-a2d7-e41007214187). You can also join our WhatsApp group chat through this [link](https://chat.whatsapp.com/JWEJn7OWvWE8MBfm2uSBhh). + +## Our Team + +This academic year, the tutorial series is being delivered by the following people: + +- [Wana](#) (Head of Tutorials) +- [Zachary Baker](#) (ML Officer) +- [Paul Chaminieu](#) (ML Officer) +- [Anna-Maria](#) (ML Officer) +- [Franciszek Nowak](#) (ML Officer - Visual Computing I) +- [James Ray](#) (ML Officer - Generative Visual Computing) + +## DOXA Challenges + +Our teaching will be supplemented by engaging AI competitions on [DOXA](https://doxaai.com/) related to topics such as visual computing, natural language processing and reinforcement learning. + +To take part and follow along with the tutorial series content, [sign up](https://doxaai.com/sign-up) to the platform if you have not done so already. + +## Weekly Tutorials + +📚 Access our notebooks, slides and recordings here! + + + +## Timeline + +### Term 1 + +During the first half term, we aim to cover basic concepts of **classical ML**: + +- Tutorial 0: **Introduction to AI** +- Tutorial 1: **Introduction to Python** +- Tutorial 2: **Regression** +- Tutorial 3: **Classification I** (Doxa) +- Tutorial 4: **Classification II** + +After reading week, we will focus on **Deep Learning**! + +- Tutorial 5: **Neural Networks** +- Tutorial 6: **Visual Computing I** (Doxa) +- Tutorial 7: **Generative visual computing** +- Tutorial 8: **Recurrent Neural Networks** (Doxa) +- Tutorial 9: **Introduction to Transforments** + +### Term 2 + +- Tutorial 10: **Natural Language Processing I** +- Tutorial 11: **Natural Language Processing II** +- Tutorial 12: **Graph Neural Networks / Reinforcement Learning** + +## Previous Seasons + +The content and resources from previous years are available on GitHub: + +- [Season 1 (2020/21)](https://github.com/UCLAIS/Machine-Learning-Tutorials) – led by [Danny Toeun Kim](https://github.com/kimdanny) +- [Season 2 (2021/22)](https://github.com/UCLAIS/ML-Tutorials-Season-2) – led by [Martynas Pocius](https://github.com/MartynasPocius) +- [Season 3 (2022/23)](https://github.com/UCLAIS/ml-tutorials-season-3) – led by [Filip Trhlík](https://trhlikfilip.com/) +- [Season 4 (2023/24)](https://github.com/UCLAIS/ml-tutorials-season-4) – led by [Angela Yu](https://github.com/angela24680403) diff --git a/our-initiatives/tutorials/GPU Computing Crash Course/_category_.json b/our-initiatives/tutorials/GPU Computing Crash Course/_category_.json new file mode 100644 index 0000000..fbc2a8a --- /dev/null +++ b/our-initiatives/tutorials/GPU Computing Crash Course/_category_.json @@ -0,0 +1,8 @@ +{ + "label": "GPU Computing Crash Course", + "position": 2, + "link": { + "type": "doc", + "id": "tutorials/GPU Computing Crash Course/index" + } +} diff --git a/our-initiatives/tutorials/GPU Computing Crash Course/index.mdx b/our-initiatives/tutorials/GPU Computing Crash Course/index.mdx new file mode 100644 index 0000000..8aeb978 --- /dev/null +++ b/our-initiatives/tutorials/GPU Computing Crash Course/index.mdx @@ -0,0 +1,61 @@ +--- +sidebar_position: 5 +--- + +import DocCardList from '@theme/DocCardList' + +# 💻 Machine Learning Tutorial Series + +Welcome to the GPU programming Crash Course + +If you have any questions about our content or machine learning more generally, feel free to ask us at the next session or make a forum post on the [UCLAIS Discord server](https://discord.gg/KSUZuQx?ltclid=3f704b3b-9044-415a-a2d7-e41007214187). You can also join our WhatsApp group chat through this [link](https://chat.whatsapp.com/JWEJn7OWvWE8MBfm2uSBhh). + +## Our Team + +This academic year, the tutorial series is being delivered by the following people: + +- [Niall Dalton](#) (Workshop lead) +- [Wana](#) (Head of Tutorials) + +## Resources + +A curated collection of resources for learning CUDA and GPU programming + +## Lectures + +**Lecture 1** – February 4, 2026 +- Location: Malet Place 1.03 +- [Slides](https://docs.google.com/presentation/d/1JgdmR_22HVcotAzSqckPpTBj2GyGADw62eUWs_iRybY/edit?usp=sharing) | [Colab](https://colab.research.google.com/drive/1NhzPcKumIunpd4fJzk_tSmcCyFVuCJ0q?usp=sharing) | [Colab Solutions](https://colab.research.google.com/drive/1WVQmMXAhcYjRnM4oeNkraO9SCiFK9KYs?usp=sharing) + +**Lecture 2** – February 11, 2026 +- Location: Malet Place 1.03 +- [Slides](https://docs.google.com/presentation/d/1esSJuDdzvHIs7k6ct7KOz1zlsjrXLt2cOSW3zMj3BVI/edit?usp=sharing) | [Colab](https://colab.research.google.com/drive/1ynqrlPfZLPIXRpcv9QzlDGMTvh7OR5BN?usp=sharing) | [Colab Solutions](https://colab.research.google.com/drive/1Xe2po0x8RE586C-0SWj_IpxrGWDYwyPP?usp=sharing) + +## Fundamentals + +- [CUDA C++ Programming Guide](https://docs.nvidia.com/cuda/cuda-c-programming-guide/) – Official NVIDIA documentation covering the CUDA programming model +- [GPU Architecture Overview](https://developer.nvidia.com/blog/cuda-refresher-cuda-programming-model/) – Understanding SMs, warps, and the memory hierarchy + +## Courses & Tutorials + +- [GPU Puzzles](https://github.com/srush/GPU-Puzzles) – Sasha Rush's interactive GPU programming puzzles +- [Stanford CS336](https://stanford-cs336.github.io/spring2025/) – Language Modeling from Scratch, covers GPU programming for LLMs +- [GPU Mode Lectures](https://github.com/gpu-mode/lectures) – Community-driven GPU programming lecture materials +- [UvA Deep Learning Tutorials](https://uvadlc-notebooks.readthedocs.io/en/latest/index.html) – Comprehensive deep learning notebooks with GPU optimization content +- [PMPP Book](https://www.amazon.com/Programming-Massively-Parallel-Processors-Hands/dp/0323912311) – Programming Massively Parallel Processors, the classic textbook + +## Tools & Libraries + +- [cuBLAS](https://developer.nvidia.com/cublas) – GPU-accelerated BLAS +- [cuDNN](https://developer.nvidia.com/cudnn) – Deep learning primitives +- [Triton](https://triton-lang.org/) – Python-like GPU programming +- [TritonParse](https://github.com/meta-pytorch/tritonparse) – Compiler tracer and visualizer +- [Nsight](https://developer.nvidia.com/nsight-systems) – Profiling and debugging + +## Advanced Topics + +- [Memory coalescing and bank conflicts](https://developer.nvidia.com/blog/how-access-global-memory-efficiently-cuda-c-kernels/) +- [Occupancy optimization](https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html#occupancy) +- [Tensor cores and mixed precision](https://developer.nvidia.com/blog/programming-tensor-cores-cuda-9/) +- [Multi-GPU programming](https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/DL2/High-performant_DL/Multi_GPU/hpdlmultigpu.html) +- [Ultra-Scale Playbook](https://huggingface.co/spaces/nanotron/ultrascale-playbook?section=profiling_gpu_compute_and_communication) – Profiling and distributed training \ No newline at end of file