Niru Maheswaranathan
13 papers · 2015–2021 · 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§
Keyword Pioneer
π
Triple Crown
π§¬
Topic Evolution
π
Trend Setter
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(59)
Venues
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(10)
Architectures
(8)
Optimization & Theory Β· Machine Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Core Methods
(4)
Interdisciplinary
(2)
Natural Language Processing
(2)
Applications
(2)
Learning Types
(2)
Models
(2)
Optimization & Theory Β· Deep Learning
(2)
Science
(2)
Techniques
(2)
Keywords
recurrent neural network
(5)
dynamical system
(3)
sentiment classification
(3)
learned optimizer
(3)
neural network optimization
(2)
gradient descent
(2)
sentiment analysis
(1)
computational neuroscience
(1)
stochastic gradient descent
(1)
attention mechanism
(1)
neural encoding
(1)
neural network interpretability
(1)
neural dynamics
(1)
sensory processing
(1)
bag-of-words model
(1)
text classification
(1)
canonical correlation analysis
(1)
semi-supervised classification
(1)
line attractor
(1)
natural language processing
(1)
Papers
Reverse engineering learned optimizers reveals known and novel mechanisms
NeurIPS 2021
The geometry of integration in text classification RNNs
ICLR 2021
Understanding How Encoder-Decoder Architectures Attend
NeurIPS 2021
How recurrent networks implement contextual processing in sentiment analysis
ICML 2020
From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
NeurIPS 2019
Guided evolutionary strategies: augmenting random search with surrogate gradients
ICML 2019
Meta-Learning Update Rules for Unsupervised Representation Learning
ICLR 2019
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
NeurIPS 2019
Understanding and correcting pathologies in the training of learned optimizers
ICML 2019
Universality and individuality in neural dynamics across large populations of recurrent networks
NeurIPS 2019
Learned Optimizers that Scale and Generalize
ICML 2017
Deep Learning Models of the Retinal Response to Natural Scenes
NeurIPS 2016
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
ICML 2015