Robust and efficient enriched representation with intrinsic neuronal heterogeneity
cs.LG, cs.NE
Submitted: 2024-12-06
Updated: 2026-10-27
Code: https://github.com/joblib/joblib
Project page: https://fbullo.github.io/ctds
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks
- A Review of Neuroscience-Inspired Machine Learning
- Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
- Deep Learning Scaling is Predictable, Empirically
- Datasets for Large Language Models: A Comprehensive Survey
- Chaos as an interpretable benchmark for forecasting and data-driven modelling
- Approximation Bounds for Random Neural Networks and Reservoir Systems
- Towards Biologically Plausible Deep Learning
- Maxout Networks
- Learning Factored Representations in a Deep Mixture of Experts
- An accurate and flexible analog emulation of AdEx neuron dynamics in silicon
- Chaos in time delay systems, an educational review
- Training Deep Neural Networks with 8-bit Floating Point Numbers
- Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
- Language Modeling on a SpiNNaker 2 Neuromorphic Chip
- Neuromorphic hardware for sustainable AI data centers
- Plastic Arbor: a modern simulation framework for synaptic plasticity -- from single synapses to networks of morphological neurons
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis