Niru Maheswaranathan

发表

Revealing computational mechanisms of retinal prediction via model reduction

Surya Ganguli, Aran Nayebi, Stephen A. Baccus, 2019 .

Learning to Learn Without Labels

Jascha Sohl-Dickstein, Niru Maheswaranathan, Brian Cheung, 2018, ICLR.

Understanding and correcting pathologies in the training of learned optimizers

Jeremy Nixon, Jascha Sohl-Dickstein, Niru Maheswaranathan, 2018, ICML.

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

Surya Ganguli, Niru Maheswaranathan, David Sussillo, 2019, NeurIPS.

Inferring hidden structure in multilayered neural circuits

Surya Ganguli, Niru Maheswaranathan, David B Kastner, 2017, bioRxiv.

Guided evolutionary strategies: augmenting random search with surrogate gradients

Jascha Sohl-Dickstein, Niru Maheswaranathan, Luke Metz, 2018, ICML.

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, Ben Poole, 2020, ArXiv.

Emergent bursting and synchrony in computer simulations of neuronal cultures

Niru Maheswaranathan, Silvia Ferrari, Craig S. Henriquez, 2012, Front. Comput. Neurosci..

Pyret: A Python package for analysis of neurophysiology data

Surya Ganguli, Niru Maheswaranathan, Benjamin Naecker, 2017, J. Open Source Softw..

Meta-Learning Biologically Plausible Semi-Supervised Update Rules

Jascha Sohl-Dickstein, Niru Maheswaranathan, Luke Metz, 2019, bioRxiv.

Line attractor dynamics in recurrent networks for sentiment classiﬁcation

Surya Ganguli, Niru Maheswaranathan, David Sussillo, 2019 .

The geometry of integration in text classification RNNs pdf

Yuan Cao, Niru Maheswaranathan, David Sussillo, 2020, ArXiv.

Training Learned Optimizers with Randomly Initialized Learned Optimizers pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, Luke Metz, 2021, ArXiv.

From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction

Surya Ganguli, Aran Nayebi, Hidenori Tanaka, 2019, NeurIPS.

Reverse engineering learned optimizers reveals known and novel mechanisms pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, David Sussillo, 2020, NeurIPS.

Deep Learning Models of the Retinal Response to Natural Scenes

Surya Ganguli, Aran Nayebi, Niru Maheswaranathan, 2017, NIPS.

Discovering Precise Temporal Patterns in Large-Scale Neural Recordings through Robust and Interpretable Time Warping

Surya Ganguli, Niru Maheswaranathan, Stephen I. Ryu, 2019, Neuron.

Deep learning models reveal internal structure and diverse computations in the retina under natural scenes

Surya Ganguli, Aran Nayebi, Niru Maheswaranathan, 2018, bioRxiv.

Inferring hidden structure in multilayered neural circuits

Surya Ganguli, Niru Maheswaranathan, Stephen A. Baccus, 2017 .

Deep Unsupervised Learning using Nonequilibrium Thermodynamics pdf

Surya Ganguli, Jascha Sohl-Dickstein, Eric A. Weiss, 2015, ICML.

Using learned optimizers to make models robust to input noise pdf

Ekin D. Cubuk, Jonathon Shlens, Niru Maheswaranathan, 2019, ArXiv.

The dynamic neural code of the retina for natural scenes

Surya Ganguli, Aran Nayebi, Hidenori Tanaka, 2019 .

Using a thousand optimization tasks to learn hyperparameter search strategies pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, Ben Poole, 2020, ArXiv.

Learned Optimizers that Scale and Generalize pdf

Misha Denil, Sergio Gomez Colmenarejo, Matthew W. Hoffman, 2017, ICML.

Learned optimizers that outperform on wall-clock and validation loss

Jeremy Nixon, Jascha Sohl-Dickstein, Niru Maheswaranathan, 2018 .

How recurrent networks implement contextual processing in sentiment analysis pdf

Niru Maheswaranathan, David Sussillo, David Sussillo, 2020, ICML.

Guided evolutionary strategies: escaping the curse of dimensionality in random search pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, Luke Metz, 2018, ArXiv.

Learning Unsupervised Learning Rules pdf

Jascha Sohl-Dickstein, Niru Maheswaranathan, Brian Cheung, 2018, ArXiv.

Discovering Precise Temporal Patterns in Large-Scale Neural Recordings through Robust and Interpretable Time Warping

Surya Ganguli, Niru Maheswaranathan, Ben Poole, 2020, Neuron.

A Multiplexed, Heterogeneous, and Adaptive Code for Navigation in Medial Entorhinal Cortex

Surya Ganguli, Niru Maheswaranathan, Lisa M. Giocomo, 2017, Neuron.

Recurrent Segmentation for Variable Computational Budgets

Jonathon Shlens, Niru Maheswaranathan, Lane McIntosh, 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Meta-Learning Update Rules for Unsupervised Representation Learning

Jascha Sohl-Dickstein, Niru Maheswaranathan, Brian Cheung, 2018, ICLR.

Universality and individuality in neural dynamics across large populations of recurrent networks

Surya Ganguli, Niru Maheswaranathan, David Sussillo, 2019, NeurIPS.

Learned optimizers that outperform SGD on wall-clock and test loss pdf

Jeremy Nixon, Jascha Sohl-Dickstein, Niru Maheswaranathan, 2018, ArXiv.

Understanding How Encoder-Decoder Architectures Attend pdf

Niru Maheswaranathan, Kyle Aitken, Yuan Cao, 2021, NeurIPS.

Time-warped PCA : simultaneous alignment and dimensionality reduction of neural data

Surya Ganguli, Stephen A. Baccus, Niru Maheswaranathan, 2016 .