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

Associative Learning01:27

Associative Learning

472
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
472
Introduction to Learning01:18

Introduction to Learning

488
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
488
Observational Learning01:12

Observational Learning

250
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
250
Cognitive Learning01:21

Cognitive Learning

460
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
460
End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

407
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
407
Neural Circuits01:25

Neural Circuits

1.3K
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...
1.3K

You might also read

Related Articles

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

Sort by
Same author

Highly efficient glycolic acid electrosynthesis from waste ethylene glycol on layered mesoporous Pd<sub>2</sub>Ni alloy.

Chemical communications (Cambridge, England)·2026
Same author

Predicting Internal Versus External Nanoparticle Formation in Zr-Based Metal-Organic Frameworks.

Journal of the American Chemical Society·2026
Same author

An Efficient Framework for Simulating Optical Responses of Dynamically Evolving Periodic Nanoarrays.

The journal of physical chemistry. A·2026
Same author

Acacetin Attenuates Heatstroke-Induced Acute Liver Injury by Targeting the c-Jun/PTGS2 Pathway.

Chemical biology & drug design·2026
Same author

Polarization-controlled operating point adjustment for optical electric field sensors in optical frequency comb undersampling systems.

Optics letters·2026
Same author

Advancing federated semi-supervised medical image segmentation: A duo of interactive denoising pseudo-labels and convolutional contrastive learning.

Medical image analysis·2026
Same journal

Distributionally Robust Feature Selection.

Advances in neural information processing systems·2026
Same journal

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution.

Advances in neural information processing systems·2026
Same journal

Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time.

Advances in neural information processing systems·2026
Same journal

JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics.

Advances in neural information processing systems·2026
Same journal

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction.

Advances in neural information processing systems·2026
Same journal

Emergence and Evolution of Interpretable Concepts in Diffusion Models.

Advances in neural information processing systems·2026
See all related articles

Related Experiment Video

Updated: Aug 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

381

Learning on Arbitrary Graph Topologies via Predictive Coding.

Tommaso Salvatori1, Luca Pinchetti1, Beren Millidge2

  • 1Department of Computer Science, University of Oxford, UK.

Advances in Neural Information Processing Systems
|April 24, 2023
PubMed
Summary
This summary is machine-generated.

Predictive coding (PC) enables training neural networks with complex, brain-like cyclic connections, overcoming limitations of standard backpropagation (BP). This new method, PC graphs, allows flexible task performance on arbitrary network topologies.

More Related Videos

Revealing Neural Circuit Topography in Multi-Color
09:11

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

15.1K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K

Related Experiment Videos

Last Updated: Aug 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

381
Revealing Neural Circuit Topography in Multi-Color
09:11

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

15.1K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Standard deep learning uses backpropagation (BP) for training, involving forward and backward passes to minimize objective functions.
  • BP's limitations include inability to train networks with cyclic or backward connections, hindering the development of brain-like architectures.
  • The neocortex's complex, heterarchical neural structure is crucial for its effectiveness, but current methods cannot replicate this.

Purpose of the Study:

  • To introduce a novel method based on predictive coding (PC) for training neural networks with arbitrary graph topologies, including cyclic connections.
  • To demonstrate the flexibility of this PC graph formulation for performing diverse tasks using the same network architecture.
  • To investigate the impact of graph topology on network performance and compare it with traditional BP methods.

Main Methods:

  • Utilized predictive coding (PC), a theory of cortical information processing, to develop a framework for inference and learning on arbitrary graph structures (PC graphs).
  • Experimentally demonstrated how PC graphs can adapt to different tasks by selectively stimulating neurons.
  • Evaluated the model's ability to handle various input structures, such as partial images, labeled images, and unlabeled images.

Main Results:

  • PC graphs successfully enable training and inference on networks with arbitrary topologies, including those with cyclic and backward connections.
  • The PC graph formulation allows for flexible task execution within a single network by altering neuronal stimulation patterns.
  • The study provides insights into how graph topology influences the performance of PC-based neural networks.

Conclusions:

  • Predictive coding offers a viable alternative to backpropagation for training complex neural network architectures, mimicking brain-like connectivity.
  • PC graphs provide a flexible and powerful framework for developing adaptable AI systems capable of handling diverse tasks and inputs.
  • Further research into graph topology's influence can optimize the design of future brain-inspired computational models.