Related Experiment Video
Updated: Mar 7, 2026
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10.9K
The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns
Pascal J Sager1,2, Jan M Deriu3, Benjamin F Grewe4
1Centre for Artificial Intelligence, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland.
Neural Computation
|March 5, 2026
Summary
We introduce the cooperative network architecture (CNA), a novel neural model for processing sensory data. This system learns and recombines components for robust, generalized pattern recognition, improving vision systems.
Area of Science:
- Computational neuroscience
- Artificial intelligence
- Computer vision
Background:
- Current vision systems face challenges with noise, deformation, and out-of-distribution data.
- Representing sensory signals effectively requires integrating local features with global structure.
Purpose of the Study:
- To introduce the cooperative network architecture (CNA) for robust sensory signal representation.
- To demonstrate unsupervised learning and flexible recombination of neural network components.
Main Methods:
- Developed a model using structured, recurrently connected neural networks ('nets').
- Learned 'net fragments' from statistical regularities in sensory input.
- Dynamically assembled nets from overlapping fragments.
Main Results:
- Demonstrated robustness to noise and deformation.
- Showcased generalization to out-of-distribution data.
- Enabled figure completion and noise resilience through unsupervised learning and recombination.
Conclusions:
- CNA offers a promising paradigm for neural representations.
- Integrates local feature processing with global structure formation.
- Provides a foundation for invariant object recognition research.
Related Concept Videos
01:25Neural Circuits
3.1K
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...
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...
3.1K
01:23Storage
452
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
452
01:11Sensory Perception: Organization of the Somatosensory System
11.6K
The somatosensory system is the central and peripheral nervous system component that senses and processes touch, pressure, pain, temperature, and body position or proprioception. The process of sensation takes place at three levels:
The receptor level:
The receptor level is the first stage of sensation. It involves the detection of a stimulus by specialized sensory receptors. The stimulus must arrive within the receptor's receptive field. Next, the receptor converts the energy of the...
The receptor level:
The receptor level is the first stage of sensation. It involves the detection of a stimulus by specialized sensory receptors. The stimulus must arrive within the receptor's receptive field. Next, the receptor converts the energy of the...
11.6K
01:27Associative Learning
1.6K
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...
Classical conditioning, also known...
1.6K
01:21Cognitive Learning
1.5K
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...
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...
1.5K
01:12Observational Learning
1.1K
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...
1.1K