Bridging Cognitive Programs and Machine Learning

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.

• Publication year

  2018

• Venue

  arXiv.org

• Publication date

  2018-02-16

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1802.06091
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative Adversarial Networks

  2021cited by this paper
• Challenging Images For Minds and Machines

  2018cited by this paper
• Deep Learning: A Critical Appraisal

  2018cited by this paper
• Investigating Human Priors for Playing Video Games

  2018cited by this paper
• Supplementary materials for: Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

  2017cited by this paper
• A survey on deep learning in medical image analysis

  2017cited by this paper
• Deep Reinforcement Learning: An Overview

  2017cited by this paper
• Failures of Deep Learning

  2017cited by this paper
• Failures of Gradient-Based Deep Learning

  2017cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Learning to Poke by Poking: Experiential Learning of Intuitive Physics

  2016cited by this paper
• Image Captioning and Visual Question Answering Based on Attributes and Their Related External Knowledge

  2016cited by this paper
• What can the brain teach us about building artificial intelligence?

  2016cited by this paper
• Semi-supervised Learning with Ladder Networks

  2015cited by this paper
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning

  2015cited by this paper
• End-to-End Training of Deep Visuomotor Policies

  2015cited by this paper
• Cognitive programs: software for attention's executive

  2014cited by this paper
• ImageNet Large Scale Visual Recognition Challenge

  2014cited by this paper
• Visual Attention in Dynamic Environments and its Application to Playing On-line Games

  2014cited by this paper
• Attentional Modulation and Selection – An Integrated Approach

  2014cited by this paper
• Deep learning in neural networks: An overview

  2014cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Playing Atari with Deep Reinforcement Learning

  2013cited by this paper
• Representing General Relational Knowledge in ConceptNet 5

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• A Computational Perspective on Visual Attention

  2011cited by this paper
• Describing objects by their attributes

  2009cited by this paper
• Modeling Visual Attention via Selective Tuning

  1995cited by this paper
• WordNet: A Lexical Database for English

  1995cited by this paper
• An inhibitory beam for attentional selection

  1994cited by this paper
• An Attentional Prototype for Early Vision

  1992cited by this paper

• Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs

  2018cites this paper