Dr. Jakob Jordan, Institute of Physiology, University of Bern.
Courtesy of Jakob Jordan
Uncovering the mechanisms of learning via synaptic plasticity is a critical step towards understanding how our brains function and building truly intelligent, adaptive machines. Researchers from the University of Bern propose a new approach in which algorithms mimic biological evolution and learn efficiently through creative evolution.
Our brains are incredibly adaptive. Every day, we form new memories, acquire new knowledge, or refine existing skills. This stands in marked contrast to our current computers, which typically only perform pre-programmed actions. At the core of our adaptability lies synaptic plasticity. Synapses are the connection points between neurons, which can change in different ways depending on how they are used. This synaptic plasticity is an important research topic in neuroscience, as it is central to learning processes and memory. To better understand these brain processes and build adaptive machines, researchers in the fields of neuroscience and artificial intelligence (AI) are creating models for the mechanisms underlying these processes. Such models for learning and plasticity help to understand biological information processing and should also enable machines to learn faster.
Algorithms mimic biological evolution
Working in the European Human Brain Project, researchers at the Institute of Physiology at the University of Bern have now developed a new approach based on so-called evolutionary algorithms. These computer programs search for solutions to problems by mimicking the process of biological evolution, such as the concept of natural selection. Thus, biological fitness, which describes the degree to which an organism adapts to its environment, becomes a model for evolutionary algorithms. In such algorithms, the “fitness” of a candidate solution is how well it solves the underlying problem.
The newly developed approach is referred to as the “evolving-to-learn” (E2L) approach or “becoming adaptive”. The research team led by Dr. Mihai Petrovici of the Institute of Physiology at the University of Bern and Kirchhoff Institute for Physics at the University of Heidelberg, confronted the evolutionary algorithms with three typical learning scenarios. In the first, the computer had to detect a repeating pattern in a continuous stream of input without receiving feedback about its performance. In the second scenario, the computer received virtual rewards when behaving in a particular desired manner. Finally, in the third scenario of “guided learning,” the computer was precisely told how much its behavior deviated from the desired one.
“In all these scenarios, the evolutionary algorithms were able to discover mechanisms of synaptic plasticity, and thereby successfully solved a new task,” says Dr. Jakob Jordan, corresponding and co-first author from the Institute of Physiology at the University of Bern. In doing so, the algorithms showed amazing creativity: “For example, the algorithm found a new plasticity model in which signals we defined are combined to form a new signal. In fact, we observe that networks using this new signal learn faster than with previously known rules,” emphasizes Dr. Maximilian Schmidt from the RIKEN Center for Brain Science in Tokyo, co-first author of the study. The results were published in the journal eLife.
“We see E2L as a promising approach to gain deep insights into biological learning principles and accelerate progress towards powerful artificial learning machines”, says Mihai Petrovoci. “We hope it will accelerate the research on synaptic plasticity in the nervous system,” concludes Jakob Jordan. The findings will provide new insights into how healthy and diseased brains work. They may also pave the way for the development of intelligent machines that can better adapt to the needs of their users.
Original Article: When algorithms get creative
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- OfficeSpace Software Receives $150 Million Strategic Investment From Vista Equity Partners to Power the Future of Hybrid Work
OfficeSpace Software, Inc., the creator of better workplaces, announced today that it has received an approximately $150 million strategic investment from Vista Equity Partners, the leading global ...
- Dusting off the Crystal Ball: What to Expect in the Evolving World of Work
We began this year by acknowledging that the box 2022 is indeed Pandora's- swirling with mixed emotions and tentative expectations. To try and predict the future is risky, even irresponsible, yet I ...
- Pixis Raises $100M in SoftBank Vision Fund 2-led Series C to Grow Its Codeless AI Infrastructure
Pixis (formerly known as Pyxis One), a leading provider of contextual codeless AI infrastructure for complete marketing optimization, today announced it has secured US $100M in Series C funding. Pixis ...
- How the relationship between live events and mobile devices is evolving in 2022
Sponsored by AdColony The pandemic has accelerated changes in the way people consume content — and live events are part of that transformation. For ...
- Evolving to a digitally focused pharmaceutical / healthcare company: An organisational roadmap
Since 2010 we’ve championed new and innovative models to reach Healthcare Professionals (HCPs), pioneering in both multi and omni-channel engagement – and we’ve always had HCP preference at the core ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Artificial learning machines
- Army Seeking Industry Input On Artificial Intelligence Solutions For IVAS
A new Request for Information released Wednesday details the Army’s interest in industry’s capabilities for developing and integrating artificial ...
- How Artificial Intelligence (AI) is Aiding Healthcare
Artificial Intelligence (AI) has transformed into one of the most powerful agents of change in healthcare over the past decade. The opportunities for healthcare organizations to start using AI and ...
- 2022 Trends in Semantic Technologies: Humanizing Artificial Intelligence
In this contributed article, editorial consultant Jelani Harper discusses how semantic technologies and tenets are some of the most effective ways to oversee enterprise use cases of AI for natural ...
- How artificial intelligence can be used to identify solar panel defects
Solar farm operators are turning to AI-powered inspection to speed up the inspection process and improve accuracy. They use algorithms that can automatically detect solar panel defects from images.
- Artificial intelligence, machine learning plays vital role in defence: DRDO director
PM Kurulkar was addressing the students and researchers at the inauguration ceremony of the two-day ‘National Conference on Communication, Computational Intelligence and Learning’ (NCCCIL) ...