We covered this in some of our earlier courses – lower batch sizes provide more updates, which should give better results for a fixed # epochs.
MACHINE LEARNING
-
Jensen Huang on Humanoid Robotics Scalability and Three AI Systems
By
–
🇫🇷 Traduit : Jensen Huang annonce le futur de la robotique.
— VISION IA (@vision_ia) 26 mai 2025
La robotique humanoïde ne marchera pas parce qu’elle est pratique. Elle marchera parce qu’elle est scalable.
3 IA pour la faire tourner :
– une pour apprendre
– une pour simuler
– une pour exécuter
Le monde se… pic.twitter.com/LfseYaGyEMTraduit : Jensen Huang annonce le futur de la robotique. La robotique humanoïde ne marchera pas parce qu’elle est pratique. Elle marchera parce qu’elle est scalable. 3 IA pour la faire tourner :
– une pour apprendre
– une pour simuler
– une pour exécuter Le monde se -
LangChain joins Snowflake DevDay June 5 San Francisco
By
–
We’re excited to be a part of #SnowflakeDevDay on June 5 in San Francisco! Get the latest in AI/ML, join a GenAI bootcamp, and connect with thousands of other builders. Register for free: https://
snowflake.com/en/summit/dev-
day/?utm_source=partner&utm_medium=langchain&utm_campaign=snowflake-partner-devday25
… -
Using Hugging Face to Host and Experiment with AI Models
By
–
Maintenant, je vais utiliser Hugging Face pour héberger mes différents modèles d'IA et espaces d'expérimentation. Suivez moi là-bas si ça vous intéresse. ( Je continuerai aussi à utiliser GitHub pour le code source. )
-
Enhancing LLM Reasoning Through Intrinsic Motivation Exploration
By
–
Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration Gao et al.: https://
arxiv.org/abs/2505.17621 #ArtificialIntelligence #DeepLearning #MachineLearning -
Agent traces better than CoT for distilling reasoning
By
–
TIL: When distilling reasoning capability from a teacher LLM to a smaller LLM, you should use Agent traces instead of CoT traces. Advantages are:
1. Increased generalization
Intuitively, this is because your agent can encounter more "surprising" results by interacting with its -
LLM Intentionality and the Herding Method for Neural Networks
By
–
Thanks Balazs. I posted the herding method. It's certainly pretty good for normalised distributions. LLM folks should probably be trying it. But I agree your argument goes beyond this. It is about whether the net has an intentional stance. Daniel Dennett offered some thoughts
-
Deterministic Algorithms for LLM Sampling Beyond Stochasticity
By
–
The LLM parrots need not be stochastic. Long weekend thought motivated by a posting by @balazskegl : A few years ago @yutianc and @wellingmax introduced me to herding. It is a dynamical systems (deterministic) algorithm for producing samples for a multinomial discrete
-
LLMs and Humans Trade Compression for Meaning Analysis
By
–
From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
Paper: https://
arxiv.org/pdf/2505.17117
v1.pdf
… -
How LLMs Organize Concepts Differently from Human Brains
By
–
Do LLMs Think Like Humans? New Study Says Not Quite This paper dives into a fascinating question:
Do Large Language Models organize concepts the way humans do?
Spoiler: They don’t—at least not yet. Humans use semantic compression—they categorize by balancing expressive