User profiles for Nishad Gothoskar
Nishad GothoskarPhD Student at MIT Verified email at mit.edu Cited by 287 |
[HTML][HTML] Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps
Cognitive maps are mental representations of spatial and conceptual relationships in an
environment, and are critical for flexible behavior. To form these abstract maps, the …
environment, and are critical for flexible behavior. To form these abstract maps, the …
3DP3: 3D scene perception via probabilistic programming
N Gothoskar, M Cusumano-Towner… - Advances in …, 2021 - proceedings.neurips.cc
We present 3DP3, a framework for inverse graphics that uses inference in a structured generative
model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent the 3D …
model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent the 3D …
Does this app really need my location? Context-aware privacy management for smartphones
The enormous popularity of smartphones, their rich sensing capabilities, and the data they
have about their users have lead to millions of apps being developed and used. However, …
have about their users have lead to millions of apps being developed and used. However, …
Smcp3: Sequential monte carlo with probabilistic program proposals
…, M Ghavamizadeh, N Gothoskar… - International …, 2023 - proceedings.mlr.press
This paper introduces SMCP3, a method for automatically implementing custom sequential
Monte Carlo samplers for inference in probabilistic programs. Unlike particle filters and …
Monte Carlo samplers for inference in probabilistic programs. Unlike particle filters and …
3d neural embedding likelihood: Probabilistic inverse graphics for robust 6d pose estimation
G Zhou, N Gothoskar, L Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
The ability to perceive and understand 3D scenes is crucial for many applications in
computer vision and robotics. Inverse graphics is an appealing approach to 3D scene …
computer vision and robotics. Inverse graphics is an appealing approach to 3D scene …
Solving the baby intuitions benchmark with a hierarchically bayesian theory of mind
To facilitate the development of new models to bridge the gap between machine and
human social intelligence, the recently proposed Baby Intuitions Benchmark (arXiv:2102.11938) …
human social intelligence, the recently proposed Baby Intuitions Benchmark (arXiv:2102.11938) …
Learning higher-order sequential structure with cloned HMMs
A Dedieu, N Gothoskar, S Swingle, W Lehrach… - arXiv preprint arXiv …, 2019 - arxiv.org
Variable order sequence modeling is an important problem in artificial and natural intelligence.
While overcomplete Hidden Markov Models (HMMs), in theory, have the capacity to …
While overcomplete Hidden Markov Models (HMMs), in theory, have the capacity to …
Query training: Learning a worse model to infer better marginals in undirected graphical models with hidden variables
M Lázaro-Gredilla, W Lehrach, N Gothoskar… - Proceedings of the …, 2021 - ojs.aaai.org
Probabilistic graphical models (PGMs) provide a compact representation of knowledge that
can be queried in a flexible way: after learning the parameters of a graphical model once, …
can be queried in a flexible way: after learning the parameters of a graphical model once, …
Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models
Sequence learning is a vital cognitive function and has been observed in numerous brain
areas. Discovering the algorithms underlying sequence learning has been a major endeavour …
areas. Discovering the algorithms underlying sequence learning has been a major endeavour …
Learning cognitive maps as structured graphs for vicarious evaluation
Cognitive maps are mental representations of spatial and conceptual relationships in an
environment. These maps are critical for flexible behavior as they permit us to navigate …
environment. These maps are critical for flexible behavior as they permit us to navigate …