User profiles for Ankani Chattoraj
Ankani ChattorajData Science Engineer, AV Behavior Testing, NVIDIA Verified email at nvidia.com Cited by 109 |
[HTML][HTML] A confirmation bias in perceptual decision-making due to hierarchical approximate inference
Making good decisions requires updating beliefs according to new evidence. This is a
dynamical process that is prone to biases: in some cases, beliefs become entrenched and …
dynamical process that is prone to biases: in some cases, beliefs become entrenched and …
Bayesian encoding and decoding as distinct perspectives on neural coding
The Bayesian brain hypothesis is one of the most influential ideas in neuroscience. However,
unstated differences in how Bayesian ideas are operationalized make it difficult to draw …
unstated differences in how Bayesian ideas are operationalized make it difficult to draw …
Relating confidence judgements to temporal biases in perceptual decision-making
A Chattoraj, M Snarskis… - Proceedings of the Annual …, 2021 - escholarship.org
Decision-making is often hierarchical and approximate in nature: decisions are not being
made based on actual observations, but on intermediate variables that themselves have to be …
made based on actual observations, but on intermediate variables that themselves have to be …
A probabilistic population code based on neural samples
Sensory processing is often characterized as implementing probabilistic inference: networks
of neurons compute posterior beliefs over unobserved causes given the sensory inputs. …
of neurons compute posterior beliefs over unobserved causes given the sensory inputs. …
Fairyted: A fair rating predictor for ted talk data
With the recent trend of applying machine learning in every aspect of human life, it is important
to incorporate fairness into the core of the predictive algorithms. We address the problem …
to incorporate fairness into the core of the predictive algorithms. We address the problem …
Weighted theta functions and embeddings with applications to max-cut, clustering and summarization
FD Johansson, A Chattoraj… - Advances in …, 2015 - proceedings.neurips.cc
We introduce a unifying generalization of the Lovász theta function, and the associated
geometric embedding, for graphs with weights on both nodes and edges. We show how it can be …
geometric embedding, for graphs with weights on both nodes and edges. We show how it can be …
[BOOK][B] Models of Approximate Inference in Vision
A Chattoraj - 2022 - search.proquest.com
To develop a complete understanding of visual perception, it is important to investigate the
system at all three levels proposed by Marr: computational goal of the visual system, algorithm…
system at all three levels proposed by Marr: computational goal of the visual system, algorithm…
A confirmation bias due to approximate active inference
Collecting new information about the outside world is a key aspect of brain function. In the
context of vision, we move our eyes multiple times per second to accumulate evidence about a …
context of vision, we move our eyes multiple times per second to accumulate evidence about a …
Diversity based edge pruning of neural networks using determinantal point processes
Deep learning architectures with huge number of parameters are often compressed using
pruning techniques. Two classes of pruning techniques are node pruning and edge pruning. A …
pruning techniques. Two classes of pruning techniques are node pruning and edge pruning. A …
Detection and mitigation of bias in ted talk ratings
Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models.
Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined …
Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined …