Peter E. Latham
11 papers · 2007–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (31) π Academic Marathon Β· Full π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π±
Topic Pioneer
π
Keyword Champion
π§
Keyword Pioneer
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(69)
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(9)
Deep Learning
(8)
Artificial Intelligence
(5)
Architectures
(4)
Core AI
(4)
Core Methods
(4)
Interdisciplinary
(3)
Science
(3)
Bayesian & Probabilistic Β· Machine Learning
(2)
Learning Types
(2)
Mathematics & Optimization
(1)
Application Areas
(1)
Bayesian & Probabilistic Β· Artificial Intelligence
(1)
Cognitive Science
(1)
Keywords
neural network
(2)
gradient descent
(2)
biological plausibility
(2)
neural network pruning
(1)
variational inference
(1)
neural coding
(1)
catastrophic forgetting
(1)
information bottleneck
(1)
neural encoding
(1)
in-context learning
(1)
ising model
(1)
energy efficiency
(1)
mutual information
(1)
hebbian learning
(1)
statistical model
(1)
model misspecification
(1)
point process
(1)
variational em
(1)
wake-sleep algorithm
(1)
representation learning
(1)
Papers
Range, not Independence, Drives Modularity in Biologically Inspired Representations
ICLR 2025
Training Dynamics of In-Context Learning in Linear Attention
ICML 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
NeurIPS 2022
Powerpropagation: A sparsity inducing weight reparameterisation
NeurIPS 2021
Towards Biologically Plausible Convolutional Networks
NeurIPS 2021
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
NeurIPS 2020
How biased are maximum entropy models?
NeurIPS 2011
Neural characterization in partially observed populations of spiking neurons
NeurIPS 2007