WeightWatcher
shapash
WeightWatcher | shapash | |
---|---|---|
4 | 8 | |
1,393 | 2,645 | |
0.4% | 0.6% | |
9.1 | 8.6 | |
20 days ago | 7 days ago | |
Python | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
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.
WeightWatcher
-
Ask HN: Have you seen anything original produced by generative AI?
These models are pretty much always extrapolating [0]
Whether the extrapolation is crude/low-rank or astute/high-rank is a question of memorization vs generalization. That gets into the question of whether or not the model is over-fitted or under-fitted. There are certain heuristics borrowed from high dimensional statistical physics that can be used to guess how good the test performance of a model will be on a typical task without even knowing what the test data is [1].
Originality for me means finding better answers to sub-tasks, and then combining those answers together in a better way. This is the nirvana of cross-entropy minimization - the emergence of capability results from gaining the ability to amass a wider range of skills, improving upon them, and percolating those improvements towards multiply the leverage of other skills.
How long such a thing can keep improving with current tech, who knows, but you should really think critically about whether that sounds just like interpolation through the corpus.
[0] Learning in High Dimension Always Amounts to Extrapolation - https://arxiv.org/abs/2110.09485
[1] https://github.com/CalculatedContent/WeightWatcher
-
Physics and Machine Learning
One of the things I love about physics is that, in addition to probably being my favorite of study in it's own right, it seems that a lot of the conceptual/mathematical content carries over and contributes to other fields. One example I've come across recently can be found here: https://github.com/CalculatedContent/WeightWatcher and here:
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
- A New Link to an Old Model Could Crack the Mystery of Deep Learning
shapash
- GitHub - MAIF/shapash: Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
-
This A.I.-generated artwork, Théâtre D'opéra Spatial, won first place at an art competition, and the art community isn't happy about it
There's work being done in that regard (like this python module), but as far as I know it's very clearly statistical guesstimates, and though it "works", the mathematical foundations are still somewhat shaky. There are heuristics in there we can't get rid of for now. But it's still better than nothing. Waaaaaay better than nothing.
-
Hacker News top posts: Jun 14, 2022
Shapash – Python library to make machine learning interpretable\ (4 comments)
- Shapash – Python library to make machine learning interpretable
-
State of the Art data drift libraries on Python?
Try out eurybia, from the author of shapash which is a brilliant library as well.
-
[P] It Is Now Possible To Generate a Model Audit Report with Shapash
With the new version of Shapash that is now available, you can document each model you release into production. Within a few lines of code, you can include in an HTML report all the information about your model (and its associated performance), the data it uses, its learning strategy, … this report is designed to be easily shared with a Data Protection Officer, an internal audit department, a risk control department, a compliance department, or anyone who wants to understand his work.
- [D] Has anyone ever used the SHAP and LIME models in machine learning?
What are some alternatives?
captum - Model interpretability and understanding for PyTorch
shap - A game theoretic approach to explain the output of any machine learning model.
TorchDrift - Drift Detection for your PyTorch Models
interpret - Fit interpretable models. Explain blackbox machine learning.
pytea - PyTea: PyTorch Tensor shape error analyzer
LIME - Tutorial notebooks on explainable Machine Learning with LIME (Original work: https://arxiv.org/abs/1602.04938)
cockpit - Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
GlassCode - This plugin allows you to make JetBrains IDEs to be fully transparent while keeping the code sharp and bright.
explainerdashboard - Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
trulens - Evaluation and Tracking for LLM Experiments
Transformer-MM-Explainability - [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
CARLA - CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms