Studies suggest that computer models called neural networks may learn to recognize patterns in data using the same algorithms as the human brain
The brain performs its canonical task — learning — by tweaking its myriad connections according to a secret set of rules. To unlock these secrets, scientists 30 years ago began developing computer models that try to replicate the learning process. Now, a growing number of experiments are revealing that these models behave strikingly similar to actual brains when performing certain tasks. Researchers say the similarities suggest a basic correspondence between the brains’ and computers’ underlying learning algorithms.
The algorithm used by a computer model called the Boltzmann machine, invented by Geoffrey Hinton and Terry Sejnowski in 1983, appears particularly promising as a simple theoretical explanation of a number of brain processes, including development, memory formation, object and sound recognition, and the sleep-wake cycle.
“It’s the best possibility we really have for understanding the brain at present,” said Sue Becker, a professor of psychology, neuroscience, and behavior at McMaster University in Hamilton, Ontario. “I don’t know of a model that explains a wider range of phenomena in terms of learning and the structure of the brain.”
Hinton, a pioneer in the field of artificial intelligence, has always wanted to understand the rules governing when the brain beefs a connection up and when it whittles one down — in short, the algorithm for how we learn. “It seemed to me if you want to understand something, you need to be able to build one,” he said. Following the reductionist approach of physics, his plan was to construct simple computer models of the brain that employed a variety of learning algorithms and “see which ones work,” said Hinton, who splits his time between the University of Toronto, where he is a professor of computer science, and Google.
During the 1980s and 1990s, Hinton — the great-great-grandson of the 19th-century logician George Boole, whose work is the foundation of modern computer science — invented or co-invented a collection of machine learning algorithms. The algorithms, which tell computers how to learn from data, are used in computer models called artificial neural networks — webs of interconnected virtual neurons that transmit signals to their neighbors by switching on and off, or “firing.” When data are fed into the network, setting off a cascade of firing activity, the algorithm determines based on the firing patterns whether to increase or decrease the weight of the connection, or synapse, between each pair of neurons.
The Latest Bing News on:
Artificial neural networks
- Arm panel PC has neural processing and PoE for industryon September 22, 2023 at 2:04 am
Estone Technology has introduced a range of Arm processor 10.1in touch-panel PCs for industrial AI applications with neural network processing, camera ...
- Enhancing nuclear power production with artificial intelligenceon September 21, 2023 at 8:04 am
Artificial intelligence (AI) holds promising potential for advancing nuclear energy production. These sophisticated computer systems mimic human logic in problem solving and decision making. With its ...
- Liquid Neural Networks Do More With Lesson September 20, 2023 at 5:00 pm
[Ramin Hasani] and colleague [Mathias Lechner] have been working with a new type of Artificial Neural Network called Liquid Neural Networks, and presented some of the exciting results at a recent ...
- Simplified optical neural network component saves space and energyon September 20, 2023 at 2:07 pm
As research into photonic computing progresses, scientists seek to optimize the performance of optical computing devices by making purpose-specific changes to their design. A team led by Bo Wu and ...
- INBRAIN’s neural platform receives breakthrough device designationon September 20, 2023 at 2:21 am
The platform leverages machine learning software that decodes therapy-specific biomarkers to deliver neuroelectronic therapy.
- How Convolutional Neural Networks Learn From Visual Inputson September 19, 2023 at 8:30 am
As machine learning and artificial intelligence advance, one technology stands out for its remarkable success in processing visual data: Convolutional Neural Networks (CNNs). These specialized forms ...
- How liquid neural networks could boost AI capabilitieson September 18, 2023 at 6:00 pm
In the automotive field, autonomous cars could obviously benefit from these liquid neural networks. This technology could help such vehicles adapt to difficult weather conditions or unforeseen, ...
- Can We Slice Up A Brain To See How Neural Networks Should Workon September 12, 2023 at 7:08 am
If you can get past the coining of yet another new word to talk about neural network designs, think about this: modeling the actual synapse can be a way to improve ...
- New photonic neural networks promise ultrafast computing for complex taskson September 12, 2023 at 7:02 am
Neural networks, inspired by networks of biological neurons, have revolutionized artificial intelligence by providing efficient solutions to complex tasks. To further unlock their potential, ...
- Revolutionary Approach to Artificial Intelligence: A New Path to Energy-Efficiencyon September 8, 2023 at 6:20 pm
Cutting-edge AI innovation in energy-efficient technology. Explore neuromorphic computing's potential to revolutionize AI, optimizing energy use while enhancing performance. Discover the key ...
The Latest Google Headlines on:
Artificial neural networks
[google_news title=”” keyword=”artificial neural networks” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
The Latest Bing News on:
- Machine learning puts virtual drug screening into high gearon September 22, 2023 at 3:34 am
Virtual screening of large compound libraries is already deployed routinely in the pharma industry to seek out potential drug candidates, but a massive increase in the number of compounds to be ...
- As the built environment changes, AI and machine learning tell a more complete storyon September 22, 2023 at 3:27 am
AI-supported monitoring of the built environment is transforming communities across the country and around the world. This article will outline some of the key ways that intelligent imaging, data ...
- Retinal Imaging And Machine Learning Honored In The 2023 Lasker Awardson September 21, 2023 at 6:00 am
The Lasker Foundation’s annual awards for medical research honor the inventors of optical coherence tomography and more.
- Machine learning models can produce reliable results even with limited training dataon September 20, 2023 at 1:40 pm
Researchers have determined how to build reliable machine learning models that can understand complex equations in real-world situations while using far less training data than is normally expected.
- Machine Learning Models Can Produce Reliable Results with Limited Training Dataon September 20, 2023 at 11:14 am
The researchers, from the University of Cambridge and Cornell University, found that for partial differential equations—a class of physics equations that describe how things in the natural world ...
- Beware! 3 Machine Learning Stocks Waving Massive Red Flags Right Nowon September 20, 2023 at 6:13 am
InvestorPlace - Stock Market News, Stock Advice & Trading Tips Though artificial intelligence and machine learning have gotten their fair ...
- Machine learning analysis of research citations highlights importance of federal funding for basic scientific researchon September 19, 2023 at 8:44 am
Biomedical research aimed at improving human health is particularly reliant on publicly funded basic science, according to a new analysis boosted by artificial intelligence.
- Early autism diagnosis breakthrough: machine learning uses eye movements on real and artificial faceson September 19, 2023 at 2:05 am
In conjunction with machine learning algorithms, Eye-tracking has emerged as a critical tool for early screening and diagnosis. Studies reveal that in ASD patients, gaze to stimuli with significant ...
- AI and Machine Learning Can Detect Polycystic Ovary Syndromeon September 19, 2023 at 1:26 am
AI and machine learning have been used to effectively detect and diagnose polycystic ovary syndrome, the most common hormone disorder in women.
- The 3 Best Machine Learning Stocks to Buy Now: September 2023on September 18, 2023 at 2:01 am
InvestorPlace - Stock Market News, Stock Advice & Trading Tips Machine learning has been the stuff of science fiction for longer than most of ...
The Latest Google Headlines on:
[google_news title=”” keyword=”machine learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]