1 code implementation • 19 Sep 2023 • Yuan Yang, Deepayan Sanyal, James Ainooson, Joel Michelson, Effat Farhana, Maithilee Kunda
We introduce a new neural architecture for solving visual abstract reasoning tasks inspired by human cognition, specifically by observations that human abstract reasoning often interleaves perceptual and conceptual processing as part of a flexible, iterative, and dynamic cognitive process.
no code implementations • 30 May 2023 • Deepayan Sanyal, Joel Michelson, Yuan Yang, James Ainooson, Maithilee Kunda
Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning.
no code implementations • 18 Feb 2023 • James Ainooson, Deepayan Sanyal, Joel P. Michelson, Yuan Yang, Maithilee Kunda
Core knowledge about physical objects -- e. g., their permanency, spatial transformations, and interactions -- is one of the most fundamental building blocks of biological intelligence across humans and non-human animals.
no code implementations • 29 Aug 2022 • Yuan Yang, Keith McGreggor, Maithilee Kunda
Raven's Progressive Matrices is a family of classical intelligence tests that have been widely used in both research and clinical settings.
no code implementations • 20 Jan 2022 • Yuan Yang, Deepayan Sanyal, Joel Michelson, James Ainooson, Maithilee Kunda
Figural analogy problems have long been a widely used format in human intelligence tests.
no code implementations • 14 Oct 2021 • Maithilee Kunda
Efforts to enhance education and broaden participation in AI will benefit from a systematic understanding of the competencies underlying AI expertise.
no code implementations • 14 Apr 2021 • Yiyuan Yang, Kenneth Li, Fernanda Eliott, Maithilee Kunda
People's visual experiences of the world are easy to carve up and examine along natural language boundaries, e. g., by category labels, attribute labels, etc.
no code implementations • 8 Oct 2020 • Zhanwen Chen, Shiyao Li, Roxanne Rashedi, Xiaoman Zi, Morgan Elrod-Erickson, Bryan Hollis, Angela Maliakal, Xinyu Shen, Simeng Zhao, Maithilee Kunda
Modern social intelligence includes the ability to watch videos and answer questions about social and theory-of-mind-related content, e. g., for a scene in Harry Potter, "Is the father really upset about the boys flying the car?"
no code implementations • 30 Sep 2020 • Maithilee Kunda, Irina Rabkina
We propose a new class of "grand challenge" AI problems that we call creative captioning---generating clever, interesting, or abstract captions for images, as well as understanding such captions.
no code implementations • 8 Feb 2020 • Tengyu Ma, Joel Michelson, James Ainooson, Deepayan Sanyal, Xiaohan Wang, Maithilee Kunda
For the problem of 3D object recognition, researchers using deep learning methods have developed several very different input representations, including "multi-view" snapshots taken from discrete viewpoints around an object, as well as "spherical" representations consisting of a dense map of essentially ray-traced samples of the object from all directions.
no code implementations • 3 Dec 2019 • Joel Michelson, Joshua H. Palmer, Aneesha Dasari, Maithilee Kunda
Learning image transformations is essential to the idea of mental simulation as a method of cognitive inference.
no code implementations • 18 Nov 2019 • Tianyu Hua, Maithilee Kunda
In this work, we investigate how Gestalt visual reasoning on the Raven's test can be modeled using generative image inpainting techniques from computer vision.
no code implementations • 19 Nov 2018 • Seunghwan Cha, James Ainooson, Maithilee Kunda
The block design test is a standardized, widely used neuropsychological assessment of visuospatial reasoning that involves a person recreating a series of given designs out of a set of colored blocks.
no code implementations • 15 Jun 2018 • Xiaohan Wang, Tengyu Ma, James Ainooson, Seunghwan Cha, Xiaotian Wang, Azhar Molla, Maithilee Kunda
In object recognition research, many commonly used datasets (e. g., ImageNet and similar) contain relatively sparse distributions of object instances and views, e. g., one might see a thousand different pictures of a thousand different giraffes, mostly taken from a few conventionally photographed angles.