How to use directed acyclic graphs to model & test causal hypotheses: https://
keithmcnulty.github.io/causal_inferen
ce_intro/#1
… …based on "Statistical Rethinking: A Bayesian Course with Examples" http://
amzn.to/41B5rJG
—
#Statistics #DataScience #Mathematics #ORMS #MachineLearning #AI #Causality #DataScientist
MACHINE LEARNING
-
Using Directed Acyclic Graphs for Causal Hypothesis Testing
By
–
-
Graph Neural Networks Foundations and Python Implementation Resources
By
–
"Graph #NeuralNetworks — Foundations, Frontiers, and Applications" at http://
amzn.to/3AAzrdv
+
Do it with #Python: http://
amzn.to/3Oj2QiG
————
#Coding #DataScience #DataScientist #GraphDB #LinkedData #KnowledgeGraph #AI #MachineLearning #DeepLearning #Algorithms -
Graph Data Modeling with Python: A Practical Guide for Data Scientists
By
–
Graph Data Modeling with #Python — A practical guide to curating, analyzing, and modeling data with graphs: http://
amzn.to/3PYxCPF via @PacktDataML ——
#DataScience #GraphDB #LinkedData #AI #MachineLearning #DataScientist
——
𝒦𝑒𝓎 𝐹𝑒𝒶𝓉𝓊𝓇𝑒𝓈: Transform relational data -
Graph Machine Learning 2nd Edition Released with PyTorch Examples
By
–
2nd Edition — New release! Order now at http://
amzn.to/45Y3LyI Graph Machine Learning — the latest advancements in graph data to build robust machine learning algorithms. 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: Master new graph ML techniques through updated examples using PyTorch -
OpenAI Agent Completes 10-Hour AtCoder Contest Autonomously
By
–
OpenAI's agent just competed in a 10hr AtCoder contest — no human help.
Started simple, then self-learned wall placements, resource reallocations, and optimized paths.
Recursive self-improvement loop? Looks like it.
This might be the first real demo of long-term autonomous -
Training Models to Reconstruct Token Embeddings from Activations
By
–
i think i see your point. the embeddings we work with are the average of many tokens’ last-layer activations. so we can’t directly load them back in, need to train a model to do it
-
World Models Research Figure Still Used Seven Years Later
By
–
Nice to see a figure from our 2018 paper about World Models is still being used in 2025. https://
worldmodels.github.io https://
arxiv.org/abs/1803.10122 -
OrbitAll: Unified Quantum Deep Learning for Molecular Systems
By
–
OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systems Accurately modeling chemical systems across diverse charges, spin states, and environments remains a central challenge in molecular machine learning. No existing machine
-
LLM Sequence Recovery Accuracy and Latent Space Configuration
By
–
it depends on sequence length, for long sentences we get about 94% back exactly. there are a lot of results in the paper (
http://
arxiv.org/abs/2310.06816) what does you mean 'set the latent space of the LLM'? -
Diffusion Infrastructure Will Outperform Autoregressive Models
By
–
one thing that in retrospect is obvious but i never considered properly is that infra for diffusion is going to outperform infra for autoregression because 1) more opportunity to optimize, 2) better open models, 3) less competition