`

Timezone: »

 
Poster
Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
Jimmy Smith · Scott Linderman · David Sussillo

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

Recurrent neural networks (RNNs) are powerful models for processing time-series data, but it remains challenging to understand how they function. Improving this understanding is of substantial interest to both the machine learning and neuroscience communities. The framework of reverse engineering a trained RNN by linearizing around its fixed points has provided insight, but the approach has significant challenges. These include difficulty choosing which fixed point to expand around when studying RNN dynamics and error accumulation when reconstructing the nonlinear dynamics with the linearized dynamics. We present a new model that overcomes these limitations by co-training an RNN with a novel switching linear dynamical system (SLDS) formulation. A first-order Taylor series expansion of the co-trained RNN and an auxiliary function trained to pick out the RNN's fixed points govern the SLDS dynamics. 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. This model removes the post-training fixed point optimization and allows us to unambiguously study the learned dynamics of the SLDS at any point in state-space. It also generalizes SLDS models to continuous manifolds of switching points while sharing parameters across switches. We validate the utility of the model on two synthetic tasks relevant to previous work reverse engineering RNNs. We then show that our model can be used as a drop-in in more complex architectures, such as LFADS, and apply this LFADS hybrid to analyze single-trial spiking activity from the motor system of a non-human primate.

Author Information

Jimmy Smith (Stanford)
Scott Linderman (Columbia University)
David Sussillo (Stanford University)

More from the Same Authors

  • 2021 : Revisiting the Structured Variational Autoencoder »
    Yixiu Zhao · Scott Linderman
  • 2021 : Bayesian Inference in Augmented Bow Tie Networks »
    Jimmy Smith · John Lawson · Scott Linderman
  • 2021 Poster: Generalized Shape Metrics on Neural Representations »
    Alex H Williams · Erin Kunz · Simon Kornblith · Scott Linderman
  • 2021 Poster: Reverse engineering learned optimizers reveals known and novel mechanisms »
    Niru Maheswaranathan · David Sussillo · Luke Metz · Ruoxi Sun · Jascha Sohl-Dickstein
  • 2020 Poster: Organizing recurrent network dynamics by task-computation to enable continual learning »
    Lea Duncker · Laura N Driscoll · Krishna V Shenoy · Maneesh Sahani · David Sussillo
  • 2019 : Poster and Coffee Break 1 »
    Aaron Sidford · Aditya Mahajan · Alejandro Ribeiro · Alex Lewandowski · Ali H Sayed · Ambuj Tewari · Angelika Steger · Anima Anandkumar · Asier Mujika · Hilbert J Kappen · Bolei Zhou · Byron Boots · Chelsea Finn · Chen-Yu Wei · Chi Jin · Ching-An Cheng · Christina Yu · Clement Gehring · Craig Boutilier · Dahua Lin · Daniel McNamee · Daniel Russo · David Brandfonbrener · Denny Zhou · Devesh Jha · Diego Romeres · Doina Precup · Dominik Thalmeier · Eduard Gorbunov · Elad Hazan · Elena Smirnova · Elvis Dohmatob · Emma Brunskill · Enrique Munoz de Cote · Ethan Waldie · Florian Meier · Florian Schaefer · Ge Liu · Gergely Neu · Haim Kaplan · Hao Sun · Hengshuai Yao · Jalaj Bhandari · James A Preiss · Jayakumar Subramanian · Jiajin Li · Jieping Ye · Jimmy Smith · Joan Bas Serrano · Joan Bruna · John Langford · Jonathan Lee · Jose A. Arjona-Medina · Kaiqing Zhang · Karan Singh · Yuping Luo · Zafarali Ahmed · Zaiwei Chen · Zhaoran Wang · Zhizhong Li · Zhuoran Yang · Ziping Xu · Ziyang Tang · Yi Mao · David Brandfonbrener · Shirli Di-Castro · Riashat Islam · Zuyue Fu · Abhishek Naik · Saurabh Kumar · Benjamin Petit · Angeliki Kamoutsi · Simone Totaro · Arvind Raghunathan · Rui Wu · Donghwan Lee · Dongsheng Ding · Alec Koppel · Hao Sun · Christian Tjandraatmadja · Mahdi Karami · Jincheng Mei · Chenjun Xiao · Junfeng Wen · Zichen (Vincent) Zhang · Ross Goroshin · Mohammad Pezeshki · Jiaqi Zhai · Philip Amortila · Shuo Huang · Mariya Vasileva · El houcine Bergou · Adel Ahmadyan · Haoran Sun · Sheng Zhang · Lukas Gruber · Yuanhao Wang · Tetiana Parshakova
  • 2018 Poster: Point process latent variable models of larval zebrafish behavior »
    Anuj Sharma · Robert Johnson · Florian Engert · Scott Linderman
  • 2018 Spotlight: Point process latent variable models of larval zebrafish behavior »
    Anuj Sharma · Robert Johnson · Florian Engert · Scott Linderman
  • 2017 : Poster Session 1 »
    Magdalena Fuchs · David Lung · Mathias Lechner · Kezhi Li · Andrew Gordus · Vivek Venkatachalam · Shivesh Chaudhary · Jan Hůla · David Rolnick · Scott Linderman · Gonzalo Mena · Liam Paninski · Netta Cohen