no code implementations • 29 Dec 2023 • Nigini Oliveira, Jasmine Li, Koosha Khalvati, Rodolfo Cortes Barragan, Katharina Reinecke, Andrew N. Meltzoff, Rajesh P. N. Rao
We therefore argue that the value system of an AI should be culturally attuned: just as a child raised in a particular culture learns the specific values and norms of that culture, we propose that an AI agent operating in a particular human community should acquire that community's moral, ethical, and cultural codes.
1 code implementation • NeurIPS 2023 • Shirui Chen, Linxing Preston Jiang, Rajesh P. N. Rao, Eric Shea-Brown
We show that the firing rate dynamics of a recurrent neural circuit with a separate set of output units can sample from an arbitrary probability distribution.
no code implementations • 15 Aug 2023 • Tommaso Salvatori, Ankur Mali, Christopher L. Buckley, Thomas Lukasiewicz, Rajesh P. N. Rao, Karl Friston, Alexander Ororbia
Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century.
no code implementations • 23 Oct 2022 • Rajesh P. N. Rao, Dimitrios C. Gklezakos, Vishwas Sathish
Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e. g., part-whole hierarchies, for equivariant vision?
no code implementations • 7 Jul 2022 • Dimitrios C. Gklezakos, Rishi Jha, Rajesh P. N. Rao
Inspired by Gibson's notion of object affordances in human vision, we ask the question: how can an agent learn to predict an entire action policy for a novel object or environment given only a single glimpse?
no code implementations • 16 Jun 2022 • Ares Fisher, Rajesh P. N. Rao
Human vision involves parsing and representing objects and scenes using structured representations based on part-whole hierarchies.
no code implementations • 14 Jan 2022 • Dimitrios C. Gklezakos, Rajesh P. N. Rao
We introduce Active Predictive Coding Networks (APCNs), a new class of neural networks that solve a major problem posed by Hinton and others in the fields of artificial intelligence and brain modeling: how can neural networks learn intrinsic reference frames for objects and parse visual scenes into part-whole hierarchies by dynamically allocating nodes in a parse tree?
no code implementations • 19 Dec 2021 • Linxing Preston Jiang, Rajesh P. N. Rao
Specifically, the Rao-Ballard hierarchical predictive coding model assumes that the top-down feedback connections from higher to lower order cortical areas convey predictions of lower-level activities.
1 code implementation • 25 Sep 2021 • Satpreet Harcharan Singh, Floris van Breugel, Rajesh P. N. Rao, Bingni Wen Brunton
Here, we take a complementary in silico approach, using artificial agents trained with reinforcement learning to develop an integrated understanding of the behaviors and neural computations that support plume tracking.
no code implementations • 6 Dec 2020 • Rajesh P. N. Rao
Brain-computer interfaces (BCIs) use decoding algorithms to control prosthetic devices based on brain signals for restoration of lost function.
1 code implementation • 23 Jan 2020 • Satpreet H. Singh, Steven M. Peterson, Rajesh P. N. Rao, Bingni W. Brunton
We show results from our approach applied to data collected for 12 human subjects over 7--9 days for each subject.
no code implementations • NeurIPS Workshop Neuro_AI 2019 • Dimitrios C. Gklezakos, Rajesh P. N. Rao
Our results show that our model can learn groups of features and their transformations directly from natural videos in a completely unsupervised manner.
no code implementations • 28 Nov 2018 • Rajesh P. N. Rao
The field of brain-computer interfaces is poised to advance from the traditional goal of controlling prosthetic devices using brain signals to combining neural decoding and encoding within a single neuroprosthetic device.
no code implementations • 23 Sep 2018 • Linxing Jiang, Andrea Stocco, Darby M. Losey, Justin A. Abernethy, Chantel S. Prat, Rajesh P. N. Rao
Two of the three subjects are "Senders" whose brain signals are decoded using real-time EEG data analysis to extract decisions about whether to rotate a block in a Tetris-like game before it is dropped to fill a line.
Human-Computer Interaction Neurons and Cognition
no code implementations • 8 Dec 2017 • Dimitrios C. Gklezakos, Rajesh P. N. Rao
Instead of discarding the rich and useful information about feature transformations to achieve invariance, we argue that models should learn object features conjointly with their transformations to achieve equivariance.
1 code implementation • 24 Sep 2017 • Kaiyu Zheng, Andrzej Pronobis, Rajesh P. N. Rao
We introduce Graph-Structured Sum-Product Networks (GraphSPNs), a probabilistic approach to structured prediction for problems where dependencies between latent variables are expressed in terms of arbitrary, dynamic graphs.