Though the brain is a very slow machine, its capabilities exceed typical state-of-the-art, ultrafast artificial intelligence algorithms; hence, a revolution in deep learning must emerge, as experimentally and theoretically demonstrated by physicists
Machine learning, introduced 70 years ago, is based on evidence of the dynamics of learning in our brain. Using the speed of modern computers and large data sets, deep learning algorithms have recently produced results comparable to those of human experts in various applicable fields, but with different characteristics that are distant from current knowledge of learning in neuroscience.
Using advanced experiments on neuronal cultures and large scale simulations, a group of scientists at Bar-Ilan University in Israel has demonstrated a new type of ultrafast artifical intelligence algorithms — based on the very slow brain dynamics — which outperform learning rates achieved to date by state-of-the-art learning algorithms.
In an article published today in the journal Scientific Reports, the researchers rebuild the bridge between neuroscience and advanced artificial intelligence algorithms that has been left virtually useless for almost 70 years.
“The current scientific and technological viewpoint is that neurobiology and machine learning are two distinct disciplines that advanced independently,” said the study’s lead author, Prof. Ido Kanter, of Bar-Ilan University’s Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center. “The absence of expectedly reciprocal influence is puzzling.”
“The number of neurons in a brain is less than the number of bits in a typical disc size of modern personal computers, and the computational speed of the brain is like the second hand on a clock, even slower than the first computer invented over 70 years ago,” he continued. “In addition, the brain’s learning rules are very complicated and remote from the principles of learning steps in current artificial intelligence algorithms,” added Prof. Kanter, whose research team includes Herut Uzan, Shira Sardi, Amir Goldental and Roni Vardi.
Brain dynamics do not comply with a well-defined clock synchronized for all nerve cells, since the biological scheme has to cope with asynchronous inputs, as physical reality develops. “When looking ahead one immediately observes a frame with multiple objects. For instance, while driving one observes cars, pedestrian crossings, and road signs, and can easily identify their temporal ordering and relative positions,” said Prof. Kanter. “Biological hardware (learning rules) is designed to deal with asynchronous inputs and refine their relative information.” In contrast, traditional artifical intelligence algorithms are based on synchronous inputs, hence the relative timing of different inputs constituting the same frame is typically ignored.
The new study demonstrates that ultrafast learning rates are surprisingly identical for small and large networks. Hence, say the researchers, “the disadvantage of the complicated brain’s learning scheme is actually an advantage”. Another important finding is that learning can occur without learning steps through self-adaptation according to asynchronous inputs. This type of learning-without-learning occurs in the dendrites, several terminals of each neuron, as was recently experimentally observed. In addition, network dynamics under dendritic learning are governed by weak weights which were previously deemed insignificant.
The idea of efficient deep learning algorithms based on the very slow brain’s dynamics offers an opportunity to implement a new class of advanced artificial intelligence based on fast computers. It calls for the reinitiation of the bridge from neurobiology to artifical intelligence and, as the research group concludes, “Insights of fundamental principles of our brain have to be once again at the center of future artificial intelligence”.
Learn more: The brain inspires a new type of artificial intelligence
The Latest on: Ultrafast artifical intelligence
[google_news title=”” keyword=”ultrafast artifical intelligence” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Ultrafast artifical intelligence
- Meta AI boss confirms the company has purchased around $30 billion worth of NVIDIA AI GPUson May 7, 2024 at 6:46 pm
Meta's AI boss, Yann LeCun, said that the company has invested $30 billion in NVIDIA AI GPUs for AI training, new Llama 3 models coming soon.
- Cubic unveils new single-case solution to enable data-rich processing in complex environmentson May 7, 2024 at 8:27 am
Cubic Defense launched a new single-case, rugged solution to enable data-rich processing in complex environments. The DTECH Fusion Edge High-Performance Compute (eHPC) was introduced on May 7 at the ...
- A potential cure for Parkinson’son May 6, 2024 at 2:00 am
AI helped researchers find five “highly potent” compounds which can stop the protein that characterizes Parkinson’s. And it helped them achieve this 10X faster and 1,000X cheaper than was otherwise ...
- Why did Musk ax the Supercharger team?on May 4, 2024 at 8:00 am
Elon Musk’s decision to dismiss much of Tesla’s Supercharger team this week came as a shock. The move poses a particular threat to charging in the U.S. and the transition to electric vehicles in the ...
- 3 5G Technology Stocks With the Potential to Make You an Overnight Millionaireon May 2, 2024 at 11:20 am
The post 3 5G Technology Stocks With the Potential to Make You an Overnight Millionaire appeared first on InvestorPlace.
- 'Our HBM chips are sold out until 2025': SK hynix CEOon May 1, 2024 at 9:03 pm
SK hynix on Thursday said that its high-bandwidth memory chips have already sold out until 2025, boasting its leadership in the advanced memory chip market for artificial intelligence. "Demand for ...
- Revolutionizing Transportation: A Glimpse into the Futureon May 1, 2024 at 9:52 am
The transportation industry stands on the cusp of a revolution. The integration of cutting-edge technology is reshaping the way we perceive and utilize transportation systems. From autonomous vehicles ...
- Driving Forward: Unveiling 10 Transformative Trends in Connected Transportation Techon May 1, 2024 at 8:14 am
Innovation is the driving force propelling us forward into a future where connectivity reigns supreme. From autonomous vehicles to smart infrastructure, the realm of connected transportation is ...
- BREAKTHROUGH : Lightsolver Makes Ultrafast Laser Based Computerson April 27, 2024 at 5:00 pm
Aerospace: Optimize material design and enhance decision intelligence for mission-critical processes in which ultra-fast processing times are needed ... technology and trends including Space, Robotics ...
- Revolutionary AI device utilizes few-molecule reservoir computing for blood glucose predictionon April 26, 2024 at 10:15 am
A collaborative research team from NIMS and Tokyo University of Science has successfully developed a cutting-edge artificial intelligence (AI) device that executes brain-like information processing ...
via Bing News