Reverse engineering recurrent networks for sentiment classification
reveals line attractor dynamics

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

25 June 2019

Niru Maheswaranathan

Alex H. Williams

Matthew D. Golub

Papers citing "Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics"

10 / 10 papers shown

Title
Trainability, Expressivity and Interpretability in Gated Neural ODEs T. Kim T. Can K. Krishnamurthy AI4CE 35 4 0 12 Jul 2023
From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning Eugene R. Rush Kaushik Jayaram J. Humbert 18 1 0 18 May 2023
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems Manuela Brenner Florian Hess Jonas M. Mikhaeil Leonard Bereska Zahra Monfared Po-Chen Kuo Daniel Durstewitz AI4CE 37 29 0 06 Jul 2022
Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management Charl Maree C. Omlin 32 1 0 20 Apr 2022
Understanding How Encoder-Decoder Architectures Attend Kyle Aitken V. Ramasesh Yuan Cao Niru Maheswaranathan 31 17 0 28 Oct 2021
Understanding Spending Behavior: Recurrent Neural Network Explanation and Interpretation Charl Maree C. Omlin AI4TS 16 5 0 24 Sep 2021
Representation learning for neural population activity with Neural Data Transformers Joel Ye C. Pandarinath AI4TS AI4CE 11 51 0 02 Aug 2021
Reverse engineering learned optimizers reveals known and novel mechanisms Niru Maheswaranathan David Sussillo Luke Metz Ruoxi Sun Jascha Narain Sohl-Dickstein 14 21 0 04 Nov 2020
Meta-trained agents implement Bayes-optimal agents Vladimir Mikulik Grégoire Delétang Tom McGrath Tim Genewein Miljan Martic Shane Legg Pedro A. Ortega OOD FedML 32 40 0 21 Oct 2020
How recurrent networks implement contextual processing in sentiment analysis Niru Maheswaranathan David Sussillo 22 22 0 17 Apr 2020