You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

1 code implementation • NeurIPS 2021 • Jimmy T. H. Smith, Scott W. Linderman, David Sussillo

The results are a trained SLDS variant that closely approximates the RNN, an auxiliary function that can produce a fixed point for each point in state-space, and a trained nonlinear RNN whose dynamics have been regularized such that its first-order terms perform the computation, if possible.

no code implementations • 29 Sep 2021 • Jordan Cotler, Kai Sheng Tai, Felipe Hernandez, Blake Elias, David Sussillo

The specific model to be emulated is determined by a \emph{model embedding vector} that the meta-model takes as input; these model embedding vectors constitute a manifold corresponding to the given population of models.

no code implementations • NeurIPS 2020 • Lea Duncker, Laura Driscoll, Krishna V. Shenoy, Maneesh Sahani, David Sussillo

Here, we develop a novel learning rule designed to minimize interference between sequentially learned tasks in recurrent networks.

no code implementations • NeurIPS 2021 • Niru Maheswaranathan, David Sussillo, Luke Metz, Ruoxi Sun, Jascha Sohl-Dickstein

Learned optimizers are algorithms that can themselves be trained to solve optimization problems.

1 code implementation • ICLR 2021 • Kyle Aitken, Vinay V. Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan

Using tools from dynamical systems analysis, we study recurrent networks trained on a battery of both natural and synthetic text classification tasks.

1 code implementation • ICML 2020 • Niru Maheswaranathan, David Sussillo

Here, we propose general methods for reverse engineering recurrent neural networks (RNNs) to identify and elucidate contextual processing.

1 code implementation • NeurIPS 2019 • Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo

To address these foundational questions, we study populations of thousands of networks, with commonly used RNN architectures, trained to solve neuroscientifically motivated tasks and characterize their nonlinear dynamics.

no code implementations • NeurIPS 2019 • Niru Maheswaranathan, Alex Williams, Matthew D. Golub, Surya Ganguli, David Sussillo

In this work, we use tools from dynamical systems analysis to reverse engineer recurrent networks trained to perform sentiment classification, a foundational natural language processing task.

no code implementations • ICML Workshop Deep_Phenomen 2019 • Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo

Recurrent neural networks (RNNs) are a powerful tool for modeling sequential data.

no code implementations • 27 Sep 2018 • Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, David Sussillo

Neural machine translation (NMT) systems have reached state of the art performance in translating text and are in wide deployment.

1 code implementation • NeurIPS 2018 • Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. K. Yamins

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet.

1 code implementation • ECCV 2018 • Guangyu Robert Yang, Igor Ganichev, Xiao-Jing Wang, Jonathon Shlens, David Sussillo

COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures.

no code implementations • 28 Nov 2017 • Lane McIntosh, Niru Maheswaranathan, David Sussillo, Jonathon Shlens

Importantly, the RNN may be deployed across a range of computational budgets by merely running the model for a variable number of iterations.

no code implementations • NeurIPS 2016 • Navdeep Jaitly, Quoc V. Le, Oriol Vinyals, Ilya Sutskever, David Sussillo, Samy Bengio

However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output sequences.

1 code implementation • 29 Nov 2016 • Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo

They can store an amount of task information which is linear in the number of parameters, and is approximately 5 bits per parameter.

no code implementations • ICML 2017 • Jakob N. Foerster, Justin Gilmer, Jan Chorowski, Jascha Sohl-Dickstein, David Sussillo

There exist many problem domains where the interpretability of neural network models is essential for deployment.

no code implementations • 19 Oct 2016 • David Sussillo, Sergey D. Stavisky, Jonathan C. Kao, Stephen I. Ryu, Krishna V. Shenoy

A major hurdle to clinical translation of brain-machine interfaces (BMIs) is that current decoders, which are trained from a small quantity of recent data, become ineffective when neural recording conditions subsequently change.

no code implementations • 22 Aug 2016 • David Sussillo, Rafal Jozefowicz, L. F. Abbott, Chethan Pandarinath

Neuroscience is experiencing a data revolution in which many hundreds or thousands of neurons are recorded simultaneously.

no code implementations • 16 Nov 2015 • Navdeep Jaitly, David Sussillo, Quoc V. Le, Oriol Vinyals, Ilya Sutskever, Samy Bengio

However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output sequences.

no code implementations • 19 Dec 2014 • David Sussillo, L. F. Abbott

We show that the successive application of correctly scaled random matrices to an initial vector results in a random walk of the log of the norm of the resulting vectors, and we compute the scaling that makes this walk unbiased.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.