Andrew Saxe

12 papers · 2009–2024 · 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 ↓

🗺️ Taxonomy Completionist (35) 🏃 Academic Marathon · Full 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

🌱 Topic Pioneer 🌟 Keyword Trendsetter Combo (5) 🧬 Topic Evolution 🧭 Keyword Pioneer 💎 Century Club · Bronze 🔥 Unstoppable · Bronze 📈 Trend Setter 🗃️ Keyword Collector (73)

Venues

NeurIPS (8) ICML (3) EACL (1)

Top co-authors

Andrew Y. Ng (2) Erin Grant (2) Sebastian Lee (2) Felix Hill (2) Clémentine Dominé (2) Sebastian Goldt (2) Aaditya Singh (1) Sam Jay Lewallen (1) Surya Ganguli (1) Stefano Mannelli (1)

Research topics

Machine Learning (12) Learning Types · Machine Learning (11) Deep Learning (9) Optimization & Theory · Machine Learning (8) Core Methods (7) Learning Types · Deep Learning (6) Architectures (5) Optimization & Theory · Deep Learning (5) Artificial Intelligence (2) Core AI (2) Computer Vision (1) Interdisciplinary (1) Analysis (1) Application Areas · Machine Learning (1) Application Areas · Deep Learning (1)

Keywords

neural network (5) representation learning (4) catastrophic forgetting (3) feature learning (3) learning dynamics (3) unsupervised learning (3) continual learning (3) multi-task learning (2) transfer learning (2) task similarity (2) receptive field (2) sparse coding (1) computer vision (1) computational neuroscience (1) domain adaptation (1) sample complexity (1) network architecture (1) unsupervised feature learning (1) in-context learning (1) knowledge transfer (1)

Papers

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NeurIPS 2024 Nonlinear dynamics of localization in neural receptive fields NeurIPS 2024 Know your audience: specializing grounded language models with listener subtraction EACL 2023 The Transient Nature of Emergent In-Context Learning in Transformers NeurIPS 2023 An Analytical Theory of Curriculum Learning in Teacher-Student Networks NeurIPS 2022 Exact learning dynamics of deep linear networks with prior knowledge NeurIPS 2022 Maslow’s Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation ICML 2022 The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022 Continual Learning in the Teacher-Student Setup: Impact of Task Similarity ICML 2021 Characterizing emergent representations in a space of candidate learning rules for deep networks NeurIPS 2020 Unsupervised learning models of primary cortical receptive fields and receptive field plasticity NeurIPS 2011 Measuring Invariances in Deep Networks NeurIPS 2009