no code implementations • 29 Dec 2023 • Kandan Ramakrishnan, R. James Cotton, Xaq Pitkow, Andreas S. Tolias
We systematically test the model under a number of different OOD generalization scenarios such as extrapolation to new object attributes, introducing new conjunctions or new attributes.
1 code implementation • 4 Oct 2023 • Rajkumar Vasudeva Raju, Zhe Li, Scott Linderman, Xaq Pitkow
Given a time series of neural activity during a perceptual inference task, our framework finds (i) the neural representation of relevant latent variables, (ii) interactions between these variables that define the brain's internal model of the world, and (iii) message-functions specifying the inference algorithm.
1 code implementation • 16 Mar 2022 • Nikos Karantzas, Emma Besier, Josue Ortega Caro, Xaq Pitkow, Andreas S. Tolias, Ankit B. Patel, Fabio Anselmi
Our results also indicate that the essential frequencies in question are effectively the ones used to achieve generalization in the first place.
no code implementations • 22 Feb 2022 • Zhe Li, Andreas S. Tolias, Xaq Pitkow
In this work we trained graph neural networks to fit time series from an example nonlinear dynamical system, the belief propagation algorithm.
2 code implementations • 18 Oct 2021 • Richard D. Lange, Ari Benjamin, Ralf M. Haefner, Xaq Pitkow
This work takes a step towards a highly flexible yet simple family of inference methods that combines the complementary strengths of sampling and VI.
no code implementations • 15 Oct 2021 • Lokesh Boominathan, Xaq Pitkow
We show that there is a non-monotonic dependence of optimal feedback gain as a function of both the computational parameters and the world dynamics, leading to phase transitions in whether feedback provides any utility in optimal inference under computational constraints.
no code implementations • 13 Oct 2021 • KiJung Yoon, Emin Orhan, Juhyun Kim, Xaq Pitkow
Neurons in the brain are complex machines with distinct functional compartments that interact nonlinearly.
no code implementations • 12 Jul 2021 • Yicheng Fei, Xaq Pitkow
A major challenge for these graphical models is that inferences such as marginalization are intractable for general graphs.
no code implementations • 1 Jan 2021 • Mengye Ren, Eleni Triantafillou, Kuan-Chieh Wang, James Lucas, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard Zemel
In this work, we consider a realistic setting where the relationship between examples can change from episode to episode depending on the task context, which is not given to the learner.
no code implementations • 15 Dec 2020 • Tara van Viegen, Athena Akrami, Kate Bonnen, Eric DeWitt, Alexandre Hyafil, Helena Ledmyr, Grace W. Lindsay, Patrick Mineault, John D. Murray, Xaq Pitkow, Aina Puce, Madineh Sedigh-Sarvestani, Carsen Stringer, Titipat Achakulvisut, Elnaz Alikarami, Melvin Selim Atay, Eleanor Batty, Jeffrey C. Erlich, Byron V. Galbraith, Yueqi Guo, Ashley L. Juavinett, Matthew R. Krause, Songting Li, Marius Pachitariu, Elizabeth Straley, Davide Valeriani, Emma Vaughan, Maryam Vaziri-Pashkam, Michael L. Waskom, Gunnar Blohm, Konrad Kording, Paul Schrater, Brad Wyble, Sean Escola, Megan A. K. Peters
Neuromatch Academy designed and ran a fully online 3-week Computational Neuroscience summer school for 1757 students with 191 teaching assistants working in virtual inverted (or flipped) classrooms and on small group projects.
no code implementations • 10 Dec 2020 • Mengye Ren, Eleni Triantafillou, Kuan-Chieh Wang, James Lucas, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard Zemel
Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge.
no code implementations • NeurIPS 2020 • Minhae Kwon, Saurabh Daptardar, Paul Schrater, Xaq Pitkow
This problem can be solved by control theory, which allows us to find the optimal actions for a given system dynamics and objective function.
no code implementations • NeurIPS 2019 • Zhe Li, Wieland Brendel, Edgar Y. Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian H. Sinz, Xaq Pitkow, Andreas S. Tolias
We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity.
no code implementations • NeurIPS 2020 • Saurabh Daptardar, Paul Schrater, Xaq Pitkow
This approach provides a foundation for interpreting the behavioral and neural dynamics of highly adapted controllers in animal brains.
1 code implementation • ICLR 2020 • A. Emin Orhan, Xaq Pitkow
In the presence of a non-linearity, orthogonal transformations no longer preserve norms, suggesting that alternative transformations might be better suited to non-linear networks.
no code implementations • 2 Feb 2019 • Arun Kumar, Zhengwei Wu, Xaq Pitkow, Paul Schrater
Estimating the structure of these internal states is crucial for understanding the neural basis of behavior.
no code implementations • 24 May 2018 • Zhengwei Wu, Paul Schrater, Xaq Pitkow
Complex behaviors are often driven by an internal model, which integrates sensory information over time and facilitates long-term planning.
1 code implementation • 21 Mar 2018 • KiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow
Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops.
1 code implementation • ICML 2018 • Renjie Liao, Yuwen Xiong, Ethan Fetaya, Lisa Zhang, KiJung Yoon, Xaq Pitkow, Raquel Urtasun, Richard Zemel
We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks.
no code implementations • ICLR 2018 • A. Emin Orhan, Xaq Pitkow
Here, we present a novel explanation for the benefits of skip connections in training very deep networks.