cs229-2018-autumn
nn
Our great sponsors
| cs229-2018-autumn | nn | |
|---|---|---|
| 112 | 26 | |
| 1,389 | 48,004 | |
| - | 8.5% | |
| 2.8 | 7.7 | |
| 14 days ago | about 1 month ago | |
| Jupyter Notebook | Jupyter Notebook | |
| - | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
cs229-2018-autumn
- cs229-2018-autumn: NEW Courses - star count:949.0
-
Mathematics courses for machine learning/deep learning.
Definitely check out CS229: https://cs229.stanford.edu/
-
Are there any books I should read to learn machine learning from scratch?
For machine learning (not deep learning), I recommend the lecture notes from Stanford's CS229 course. The reason I really like these notes is because you can find past problem sets that went along with them, and the problem sets are very good: difficult but not impossible, and close to a 50/50 mix of math and programming. I never feel like I've learned a topic just from reading about it, so having good problems to go along with the reading was very important to me.
- cs229-2018-autumn: NEW Courses - star count:834.0
nn
-
Can't remember name of website that has explanations side-by-side with code
Hey are you talking about https://nn.labml.ai/ ?
- [D] Recent ML papers to implement from scratch
-
[P] GPT-NeoX inference with LLM.int8() on 24GB GPU
Implementation & LM Eval Harness Results
-
[P] Fine-tuned the GPT-Neox Model to Generate Quotes
Github: https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/neox
-
Best resources to learn recent transformer papers and stay updated [D]
Regarding implementations this helps me: https://nn.labml.ai/
- Introductory papers to implement
- How to convert research papers to code?
-
[D] How to convert papers to code?
Dunno if this is directly helpful, but this website has implementation with the math side by side https://nn.labml.ai/
- [D] Looking for open source projects to contribute
- Resource for papers explanation
What are some alternatives?
cs229-2019-summer - All notes and materials for the CS229: Machine Learning course by Stanford University
GFPGAN-for-Video-SR - A colab notebook for video super resolution using GFPGAN
stanford-CS229 - Python solutions to the problem sets of Stanford's graduate course on Machine Learning, taught by Prof. Andrew Ng [UnavailableForLegalReasons - Repository access blocked]
labml - 🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱
stanford-cs229 - 🤖 Exercise answers to the problem sets from the 2017 machine learning course cs229 by Andrew Ng at Stanford
functorch - functorch is JAX-like composable function transforms for PyTorch.
probability - Probabilistic reasoning and statistical analysis in TensorFlow
ZoeDepth - Metric depth estimation from a single image
Machine-Learning-Specialization-Coursera - Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG
onnx-simplifier - Simplify your onnx model
huggingface_hub - The official Python client for the Huggingface Hub.
Basic-UI-for-GPT-J-6B-with-low-vram - A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.