Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Reason and Intuition01:37

Reason and Intuition

6.4K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
6.4K
Reasoning01:30

Reasoning

66
Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
66
Neural Circuits01:25

Neural Circuits

1.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.1K
Deductive Reasoning01:16

Deductive Reasoning

55.0K
Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
55.0K
Inductive Reasoning00:59

Inductive Reasoning

60.1K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
60.1K
Introduction to Cognitive Psychology01:20

Introduction to Cognitive Psychology

431
Cognitive psychology is the field of psychology dedicated to examining how people think. It attempts to explain how and why we think the way we do by studying the interactions among human thinking, emotion, creativity, language, and problem-solving, as well as other cognitive processes. Cognitive psychology studies how information is processed and manipulated in remembering, thinking, and knowing.
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
431

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A novel dynamic risk score to predict clinically significant bleeding after 3 months of anticoagulation in patients with incident venous thromboembolism and without active cancer.

Journal of thrombosis and haemostasis : JTH·2026
Same author

A novel dynamic risk score to predict venous thromboembolism recurrences after 3 months of anticoagulation in patients with incident venous thromboembolism and without active cancer.

Journal of thrombosis and haemostasis : JTH·2026
Same author

DataSHIELD: mitigating disclosure risk in a multi-site federated analysis platform.

Bioinformatics advances·2025
Same author

Generating Complex Explanations for Artificial Intelligence Models: An Application to Clinical Data on Severe Mental Illness.

Life (Basel, Switzerland)·2024
Same author

Single-cell subcellular protein localisation using novel ensembles of diverse deep architectures.

Communications biology·2023
Same author

dsSynthetic: synthetic data generation for the DataSHIELD federated analysis system.

BMC research notes·2022

Related Experiment Video

Updated: Jun 7, 2025

The Adventures of Fundi Intervention Based on the Cognitive and Emotional Processing in Attention Deficit Hyperactive Disorder Patients
05:48

The Adventures of Fundi Intervention Based on the Cognitive and Emotional Processing in Attention Deficit Hyperactive Disorder Patients

Published on: June 12, 2020

5.7K

Neural networks for abstraction and reasoning.

Mikel Bober-Irizar1, Soumya Banerjee2

  • 1University of Cambridge, Cambridge, UK.

Scientific Reports
|November 13, 2024
PubMed
Summary

Researchers explored novel AI approaches for the Abstraction & Reasoning Corpus (ARC), a challenging benchmark for broad generalization. While neural networks and large language models show promise, they still lag behind hand-crafted rules, suggesting diverse strategies are key for AI reasoning.

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

995

Related Experiment Videos

Last Updated: Jun 7, 2025

The Adventures of Fundi Intervention Based on the Cognitive and Emotional Processing in Attention Deficit Hyperactive Disorder Patients
05:48

The Adventures of Fundi Intervention Based on the Cognitive and Emotional Processing in Attention Deficit Hyperactive Disorder Patients

Published on: June 12, 2020

5.7K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

995

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Cognitive Science

Background:

  • Artificial intelligence (AI) has long aimed to replicate human abstraction and reasoning, enabling systems to learn from minimal examples.
  • Despite advances in neural networks, achieving broad generalization beyond training data remains a significant challenge for AI.
  • The Abstraction & Reasoning Corpus (ARC) was developed to rigorously test AI's broad generalization capabilities on abstract visual reasoning tasks.

Purpose of the Study:

  • To investigate novel approaches for solving the Abstraction & Reasoning Corpus (ARC) tasks, focusing on broad generalization.
  • To evaluate the effectiveness of recent neural network advancements and neurosymbolic methods against existing hand-crafted solvers for ARC.
  • To explore the potential of large language models (LLMs) and ensemble methods in addressing the challenges posed by ARC.

Main Methods:

  • Adapted the DreamCoder neurosymbolic reasoning solver, introducing the Perceptual Abstraction and Reasoning Language (PeARL) for improved ARC task performance.
  • Developed a new recognition model and an encoding/augmentation scheme to enable large language models (LLMs) to tackle ARC tasks.
  • Conducted an ensemble analysis combining diverse AI systems to assess synergistic performance and identify individual system strengths.

Main Results:

  • The adapted DreamCoder system, incorporating PeARL and a new recognition model, significantly improved upon previous neurosymbolic approaches for ARC.
  • Large language models (LLMs) demonstrated the ability to solve a subset of ARC tasks, complementing the performance of other state-of-the-art solvers.
  • Ensemble models achieved superior results compared to individual systems, highlighting the potential benefits of combining diverse AI strategies for complex reasoning.

Conclusions:

  • Current neural network-based approaches, including LLMs, still underperform compared to traditional hand-crafted solvers on the ARC benchmark.
  • A diversity of methods, potentially inspired by human cognitive strategies, may be essential for achieving robust performance on broad generalization tasks like ARC.
  • The release of the arckit Python library aims to facilitate future research and development in AI abstraction and reasoning.