Related Experiment Video
Updated: Jul 19, 2025
11:18
Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
Published on: June 1, 2015
10.7K
Bio-inspired, task-free continual learning through activity regularization
Francesco Lässig1, Pau Vilimelis Aceituno2, Martino Sorbaro2,3
1Institute of Neuroinformatics University of Zürich and ETH, Zürich, Switzerland. flaessig@ethz.ch.
Biological Cybernetics
|August 17, 2023
Summary
This study introduces a novel continual learning (CL) method inspired by brain function, using sparse representations and recurrent connections to prevent catastrophic forgetting without needing task boundaries.
Area of Science:
- Neuroscience
- Deep Learning
- Artificial Intelligence
Background:
- Continual learning (CL) in deep learning struggles with catastrophic forgetting, unlike biological brains.
- Existing CL methods often require predefined task boundaries, limiting real-world applicability.
Purpose of the Study:
- To develop a biologically inspired, task-free continual learning algorithm.
- To investigate the role of sparse neuronal representations and recurrent connections in preventing catastrophic forgetting.
Main Methods:
- Implemented a sparse-recurrent version of Deep Feedback Control (DFC).
- Combined DFC with winner-take-all sparsity and lateral recurrent connections.
- Evaluated the method on the split-MNIST computer vision benchmark.
Main Results:
- The combination of sparsity and intra-layer recurrent connections significantly improved CL performance over standard backpropagation.
- The proposed method achieved performance comparable to established CL techniques like EWC and Synaptic Intelligence.
- The approach successfully learned without requiring explicit task boundary information.
Conclusions:
- Biologically inspired computational principles can lead to effective task-free continual learning algorithms.
- Sparse representations and recurrent connections are crucial for robust continual learning.
- This work offers a promising direction for developing more adaptable and brain-like artificial intelligence.
More Related Videos
Related Concept Videos
01:12Observational Learning
209
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...
209
01:22Purposive Learning
141
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
141
01:21Cognitive Learning
421
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...
421
01:18Introduction to Learning
471
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...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
471
01:27Associative Learning
441
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...
441
01:14Avoidance Learning and Learned Helplessness
1.8K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.8K