pysindy
pysindy | grade-school-math | |
---|---|---|
5 | 4 | |
1,293 | 880 | |
2.8% | 4.7% | |
9.3 | 0.0 | |
10 days ago | 3 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | - |
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.
pysindy
- Sam Altman's ouster was precipitated by letter to board about AI breakthrough
-
Ask HN: Why don't datacenters have passive rooflines like Net Zero homes?
https://github.com/dynamicslab/pysindy/issues/383#event-1002...
awesome-machine-learning-fluid-mechanics >
- Why are neural networks not multi-dimensional?
- Creating an equation for a system given its data.
-
Physics-Based Deep Learning Book
Not MLP, but PySindy[0] might be a way to find a closed form solution. A simple MLP may not be best way to achieve what are you are after.
[0] https://github.com/dynamicslab/pysindy
grade-school-math
-
Sam Altman's ouster was precipitated by letter to board about AI breakthrough
GPT-4 scores 0.92 on that one. A breakthrough could mean it gets all of them correct.
This would have major implications for long-term planning. For instance, if you have a sequence of 10 steps, each with a 90% success rate, the overall success rate after all 10 steps falls to just 34%. This is one of the reasons why agents like AutoGPT often fail in complex tasks.
[1] https://github.com/openai/grade-school-math
-
"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them", Google Research 2022 (PaLM + CoT achieves superhuman performance on 10 out of 23 BIG-Bench Hard tasks, and OpenAI Codex + CoT on 17 out of 23 tasks)
The same concept was described earlier in original gsm8k paper as "socratic dialog": https://github.com/openai/grade-school-math/blob/master/grade_school_math/data/test_socratic.jsonl
- OpenAI обучила языковую модель решать математические задачки
What are some alternatives?
sysidentpy - A Python Package For System Identification Using NARMAX Models
torchsde - Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Poincare-Maps - MATLAB files for discovery of Poincaré maps
thebe - Turn static HTML pages into live documents with Jupyter kernels.
pbdl-book - Welcome to the Physics-based Deep Learning Book (v0.2)
diffrax - Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Stochastic-Processes - My book: Gentle Introduction to Chaotic Dynamical Systems. Includes stochastic dynamical systems and statistical properties of numeration systems in any dimension.
awesome-machine-learning-fluid-mechanics - Curated list for ML in FM
awesome-machine-learning-fluid-m
awesome-fluid-dynamics - A curated list of repositories related to fluid dynamics.
open-sustainable-technology - A directory and analysis of the open source ecosystem in the areas of climate change, sustainable energy, biodiversity and natural resources.