The Center for Brains, Minds, and Machines (CBMM) was an NSF-funded science and technology center focused on the interdisciplinary study of intelligence and how it can be replicated in machines. After over a decade of inspiring collaborative research, CBMM's funding ended on August 31, 2025. Many CBMM researchers also work with the Quest.
The BMM Summer Course is continuing; the most recent session took place in Woods Hole, MA, from August 3 to August 24, 2025.
Recent CBMM Memos
-
2025/07/01
Multiplicative Regularization Generalizes Better Than Additive Regularization
-
2025/07/01
Position: A Theory of Deep Learning Must Include Compositional Sparsity
-
2025/01/31
On efficiently computable functions, deep networks and sparse compositionality
-
2024/12/27
Self-Assembly of a Biologically Plausible Learning Circuit
-
2024/10/10
On Generalization Bounds for Neural Networks with Low Rank Layers
-
2024/10/06
Formation of Representations in Neural Networks
-
2024/09/26
On the Power of Decision Trees in Auto-Regressive Language Modeling
-
2024/07/12
For HyperBFs AGOP is a greedy approximation to gradient descent
-
2024/02/07
Compositional Sparsity of Learnable Functions
-
2023/12/20
The Janus effects of SGD vs GD: high noise and low rank