David Sussillo
11 papers · 2016–2021 · 4 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (24)
π§
Keyword Pioneer
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Conference Pioneer
Venues
Top co-authors
Research topics
Deep Learning
(10)
Artificial Intelligence
(8)
Core AI Β· Artificial Intelligence
(8)
Machine Learning
(7)
Architectures
(7)
Core Methods
(4)
Learning Types Β· Deep Learning
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Applications
(2)
Learning Types Β· Machine Learning
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Analysis
(1)
Core AI Β· Computer Vision
(1)
Keywords
recurrent neural network
(8)
dynamical system
(4)
sentiment classification
(3)
fixed point
(2)
text classification
(1)
bag-of-words model
(1)
neural dynamics
(1)
linear methods
(1)
natural language processing
(1)
dynamic programming
(1)
gradient descent
(1)
canonical correlation analysis
(1)
neural network optimization
(1)
line attractor
(1)
learning rate adaptation
(1)
object classification
(1)
natural language
(1)
text modeling
(1)
feedback connections
(1)
network dynamics
(1)
Papers
Reverse engineering learned optimizers reveals known and novel mechanisms
NeurIPS 2021
Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
NeurIPS 2021
The geometry of integration in text classification RNNs
ICLR 2021
How recurrent networks implement contextual processing in sentiment analysis
ICML 2020
Organizing recurrent network dynamics by task-computation to enable continual learning
NeurIPS 2020
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
NeurIPS 2019
Universality and individuality in neural dynamics across large populations of recurrent networks
NeurIPS 2019
A Dataset and Architecture for Visual Reasoning with a Working Memory
ECCV 2018
Task-Driven Convolutional Recurrent Models of the Visual System
NeurIPS 2018
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
ICML 2017
An Online Sequence-to-Sequence Model Using Partial Conditioning
NeurIPS 2016