Skip to content
conftrace_

Peter E Latham

3 papers · 2021–2022 · 1 venue · 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 ↓
🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

NeurIPS (3)

Top co-authors

Peter E. Latham (3) Timothy Lillicrap (2) Yash Mehta (2) Jonathan Schwarz (1) Roman Pogodin (1) Naoki Hiratani (1) Razvan Pascanu (1) Yee W. Teh (1) Siddhant Jayakumar (1)

Research topics

Deep Learning (3) Machine Learning (3) Optimization & Theory (2) Artificial Intelligence (1) Application Areas (1) Architectures (1) Core AI (1) Core Methods (1) Learning Types (1) Techniques (1)

Keywords

model compression (1) neural network pruning (1) catastrophic forgetting (1) gradient descent (1) model pruning (1) biological plausibility (1) weight sharing (1) lateral connectivity (1) hebbian plasticity (1) biologically plausible learning (1) synaptic weight (1) convolutional network (1) sparse training (1) deep linear network (1) weight normalization (1) learning stability (1) neural network (1) weight parameterization (1) weight parameterisation (1) node perturbation (1)

Papers

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