Peter E. Latham
11 papers · 2007–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (10) π Conference Polyglot (3)
π
Conference Polyglot
(3)
π
Academic Marathon
(18)
π
Cross-Pollinator
(8)
π±
Topic Pioneer
π
Keyword Champion
π
Trend Setter
ποΈ
Keyword Collector
(50)
π
Century Club
(11)
β
The Questioner
π₯
Unstoppable
(6)
Conferences
NIPS (6)
ICML (3)
ICLR (2)
Top co-authors
Research topics
Keywords
biological plausibility
(2)
neural network pruning
(1)
wake-sleep algorithm
(1)
variational inference
(1)
model misspecification
(1)
information bottleneck
(1)
neural encoding
(1)
ising model
(1)
mutual information
(1)
hebbian learning
(1)
statistical model
(1)
gradient descent
(1)
point process
(1)
variational em
(1)
catastrophic forgetting
(1)
neural connectivity
(1)
sensory stimuli
(1)
model pruning
(1)
divisive normalization
(1)
model compression
(1)
Papers
Training Dynamics of In-Context Learning in Linear Attention
ICML 2025
Range, not Independence, Drives Modularity in Biologically Inspired Representations
ICLR 2025
Understanding Unimodal Bias in Multimodal Deep Linear Networks
ICML 2024
Actionable Neural Representations: Grid Cells from Minimal Constraints
ICLR 2023
Meta-Learning the Inductive Bias of Simple Neural Circuits
ICML 2023
On the Stability and Scalability of Node Perturbation Learning
NIPS 2022
Powerpropagation: A sparsity inducing weight reparameterisation
NIPS 2021
Towards Biologically Plausible Convolutional Networks
NIPS 2021
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
NIPS 2020
How biased are maximum entropy models?
NIPS 2011
Neural characterization in partially observed populations of spiking neurons
NIPS 2007