Bridging Cognitive Programs and Machine Learning

02/16/2018
by   Amir Rosenfeld, et al.
0

While great advances are made in pattern recognition and machine learning, the successes of such fields remain restricted to narrow applications and seem to break down when training data is scarce, a shift in domain occurs, or when intelligent reasoning is required for rapid adaptation to new environments. In this work, we list several of the shortcomings of modern machine-learning solutions, specifically in the contexts of computer vision and in reinforcement learning and suggest directions to explore in order to try to ameliorate these weaknesses.

READ FULL TEXT
research
10/02/2020

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Humans have an inherent ability to learn novel concepts from only a few ...
research
02/13/2018

Challenging Images For Minds and Machines

There is no denying the tremendous leap in the performance of machine le...
research
05/27/2021

Unsupervised Domain Adaption of Object Detectors: A Survey

Recent advances in deep learning have led to the development of accurate...
research
02/13/2019

Can We Automate Diagrammatic Reasoning?

Learning to solve diagrammatic reasoning (DR) can be a challenging but i...
research
06/23/2022

Agriculture-Vision Challenge 2022 – The Runner-Up Solution for Agricultural Pattern Recognition via Transformer-based Models

The Agriculture-Vision Challenge in CVPR is one of the most famous and c...
research
02/12/2017

A Spacetime Approach to Generalized Cognitive Reasoning in Multi-scale Learning

In modern machine learning, pattern recognition replaces realtime semant...
research
04/02/2019

A Game of Dice: Machine Learning and the Question Concerning Art

We review some practical and philosophical questions raised by the use o...

Please sign up or login with your details

Forgot password? Click here to reset