Related Experiment Video
Updated: Jan 23, 2026
11:18
Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
Published on: June 1, 2015
11.1K
Neuromorphic Hardware Learns to Learn
Thomas Bohnstingl1, Franz Scherr1, Christian Pehle2
1Institute for Theoretical Computer Science, Graz University of Technology, Graz, Austria.
Frontiers in Neuroscience
|June 11, 2019
Summary
Gradient-free optimization tools and meta-plasticity enhance neuromorphic hardware learning. This approach enables efficient reward-based learning and demonstrates Learning-to-Learn capabilities for accelerated task acquisition.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Computer Engineering
Background:
- Neuromorphic hardware typically relies on manually selected hyperparameters and learning algorithms.
- Biological neural networks are optimized through evolution and development for diverse tasks.
- Existing emulation methods like genetic algorithms have limitations in scope and require manual design.
Purpose of the Study:
- To adapt biological optimization processes for neuromorphic hardware using advanced gradient-free tools.
- To enhance the reward-based learning efficiency of neuromorphic agents.
- To demonstrate Learning-to-Learn capabilities on neuromorphic hardware.
Main Methods:
- Employing gradient-free optimization tools, specifically cross-entropy methods and evolutionary strategies.
- Implementing meta-plasticity to optimize learning rules within the hardware.
- Utilizing accelerated neuromorphic hardware for large-scale network computations.
Main Results:
- Optimization algorithms significantly improve neuromorphic agents' learning efficiency from rewards.
- Meta-plasticity substantially enhances the reward-based learning capabilities of the hardware.
- Demonstrated Learning-to-Learn benefits, including abstract knowledge extraction for faster learning on related tasks.
Conclusions:
- Gradient-free optimization and meta-plasticity are effective for neuromorphic hardware.
- Neuromorphic hardware can achieve efficient reward-based learning and Learning-to-Learn.
- This approach holds promise for advancing AI and neuromorphic computing capabilities.
Related Concept Videos
01:14Avoidance Learning and Learned Helplessness
2.5K
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...
2.5K
01:25Learning Disabilities
581
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
Dyslexia
Dyslexia is a...
581
01:27Associative Learning
1.3K
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...
1.3K
01:22Purposive Learning
457
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...
457
01:12Observational Learning
863
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...
863
01:18Introduction to Learning
1.0K
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...
1.0K