via KAIST
A KAIST team shows that primitive visual selectivity of faces can arise spontaneously in completely untrained deep neural networks
Researchers have found that higher visual cognitive functions can arise spontaneously in untrained neural networks. A KAIST research team led by Professor Se-Bum Paik from the Department of Bio and Brain Engineering has shown that visual selectivity of facial images can arise even in completely untrained deep neural networks.
This new finding has provided revelatory insights into mechanisms underlying the development of cognitive functions in both biological and artificial neural networks, also making a significant impact on our understanding of the origin of early brain functions before sensory experiences.
The study published in Nature Communications on December 16 demonstrates that neuronal activities selective to facial images are observed in randomly initialized deep neural networks in the complete absence of learning, and that they show the characteristics of those observed in biological brains.
The ability to identify and recognize faces is a crucial function for social behavior, and this ability is thought to originate from neuronal tuning at the single or multi-neuronal level. Neurons that selectively respond to faces are observed in young animals of various species, and this raises intense debate whether face-selective neurons can arise innately in the brain or if they require visual experience.
Using a model neural network that captures properties of the ventral stream of the visual cortex, the research team found that face-selectivity can emerge spontaneously from random feedforward wirings in untrained deep neural networks. The team showed that the character of this innate face-selectivity is comparable to that observed with face-selective neurons in the brain, and that this spontaneous neuronal tuning for faces enables the network to perform face detection tasks.
These results imply a possible scenario in which the random feedforward connections that develop in early, untrained networks may be sufficient for initializing primitive visual cognitive functions.
Professor Paik said, “Our findings suggest that innate cognitive functions can emerge spontaneously from the statistical complexity embedded in the hierarchical feedforward projection circuitry, even in the complete absence of learning”.
He continued, “Our results provide a broad conceptual advance as well as advanced insight into the mechanisms underlying the development of innate functions in both biological and artificial neural networks, which may unravel the mystery of the generation and evolution of intelligence.” This work was supported by the National Research Foundation of Korea (NRF) and by the KAIST singularity research project.
Original Article: Face Detection in Untrained Deep Neural Networks?
More from: Korea Advanced Institute of Science and Technology
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Untrained neural networks
- Scientists regenerate neural pathways in mice with cells from rats
Two independent research teams have successfully regenerated mouse brain circuits in mice using neurons grown from rat stem cells. Both studies, published April 25 in the journal Cell, offer valuable ...
- MCU-based AI tool detects visual anomalies rather than known features
Edge Impulse has introduced AI software for Arm microcontrollers and Nvidia processors intended to spot previously unseen and untrained anomalies in images ... ‘Gaussian mixture models’ – GMMs.
- Unifying network model links recency and central tendency biases in working memory
Seemingly disparate working memory biases, including short-term serial and contraction biases, may arise from a common mechanism via the interaction of multiple networks, each operating over a ...
- Network model unifies recency and central tendency biases
Neuroscientists have revealed that recency bias in working memory naturally leads to central tendency bias, the phenomenon where people's (and animals') judgements are biased towards the average of ...
- Essential Jewelry for Every Woman
When selecting jewelry, several criteria must be considered: individual features, fashion trends, cultural preferences, and modern technologies. Let's explore these in order. Read more: Essential Jewe ...
Go deeper with Google Headlines on:
Untrained neural networks
[google_news title=”” keyword=”untrained neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Artificial neural networks
- From baby talk to baby artificial intelligence
We ask a lot of ourselves as babies. Somehow, we must grow from sensory blobs into mobile, rational, attentive communicators in just a few years.
- Apple Targets Google Staff To Build Artificial Intelligence Team
Apple has poached dozens of artificial intelligence experts from Google and has created a secretive European laboratory in Zurich, as the tech giant ...
- ATPBot Introduces Advanced AI Trading Bot Leveraging Supercomputers and Neural Networks
Efficient and Stable Trading Strategies Powered by AI Focusing on the development of quantitative trading strategies, ATPBot leverages artificial intelligence to optimize and execute these strategies.
- How Artificial Intelligence is Revolutionizing Art, Music & Literature?
How Artificial Intelligence is Revolutionizing Art, Music, and Literature. It has long been believed that creativity represents the highest level of human inven ...
- Neural Networks And AI's Rapid Progression Ignite A Multi-Trillion-Dollar Economic Shift
Neural Networks and AI's Rapid Progression Ignite a Multi-Trillion-Dollar Economic Shift Collective Audience Takes off on Insticator Link ...
Go deeper with Google Headlines on:
Artificial neural networks
[google_news title=”” keyword=”artificial neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]