Teach the computer to see like a human eye

Does the picture change? Artificial neural networks will have a hard time deciphering it

Artificial intelligence is a branch of computer science that studies the ability to program computers to act like the human brain. At its core is deep learning (Deep Learning) - algorithms that allow computer systems to learn from previous examples and experiences, and thus perform a variety of computational tasks.

Prof. Yair Weiss from the School of Engineering and Computer Science at the Hebrew University researches artificial intelligence, deep learning and computer vision (a field that studies how computers analyze images to extract visual information from them and interpret it). One of the main topics he focuses on - which combines these three areas - is artificial neuron networks (nerve cells). It is a computational mathematical model (algorithms) developed inspired by the neuron networks that exist in the human brain. The artificial neural networks consist of many information units (input and output) linked to each other using numbers and transfer data from one to another, based on deep learning. Each number expresses the strength of the connection between them, and ultimately the connectivity creates intelligence. Thus, these networks can be used in almost all computer applications. For example, identifying objects in photos and videos, deciphering medical simulations, robotics and autonomous transportation.

In the last decade, artificial neural networks were built that led to breakthroughs in many fields, including computer vision. According to Prof. Weiss, "Deep learning - which neural networks are based on - and computer vision go hand in hand. In our research we try to teach computers to see similar to the human eye. We give them many examples (input) and thus, using the neural networks, they are supposed to learn to see - for example to identify details in pictures and differentiate between them. Using the examples we actually change the numbers that connect the neurons, until we get the desired result. ie the exact output. For example, we upload many pictures of dogs and cats to the computer, this activates neurons that recognize them, and they are supposed to decide what is a dog and what is a cat."

"However," notes Prof. Weiss, "these networks are not yet sufficiently developed as the human brain. They can make significant calculation errors only due to small changes in the examples. For example, if we move an image of a dog by one pixel, the computer may recognize it as a different animal, which of course will not happen to the human vision system; A human being will decode an image accurately even if it changes a little." What is the question? Why do artificial neural networks fail and what needs to be done to make them work better?

Therefore, Prof. Weiss and his team are focusing on developing the neural networks, so that they can generalize better and be more accurate in recognition. In their latest study - which won a research grant from the National Science Foundation - the scientists wanted to check why they fail and how they could work better. They embedded them in computers and showed them pictures, for example of animals. At first they recognized the content of the images accurately, but when the researchers made slight changes to them, for example moving them a pixel to the right or making them slightly larger, the neural networks got 'confused'. For example, they identified a ferret as a cat or a sea lion.

After that, the researchers conducted a mathematical analysis of the data and discovered that the reason for the networks' failures is the sampling theorem; This mathematical theorem explains, among other things, the relationship between images and the pixel sampling in them; How much information in sampled pixels is required to reconstruct an image. The researchers found that the networks do not fulfill the sampling theorem in the pixel sampling process, and therefore make mistakes in recognizing the image when it changes slightly. Today they are trying to fix this - to teach the networks to fulfill the sampling theorem within a short calculation time.

We are trying to teach computers to see similar to the human eye. We give them many examples (input) and thus, using the neural networks, they are supposed to learn to see - for example to identify details in pictures and differentiate between them

Says Prof. Weiss: "We realized that the artificial neural networks are not yet resistant to small changes. When they are taken out of their comfort zone, they fail. Therefore at this stage it is not certain that they can be trusted in various computer applications. For example, if a camera in an autonomous vehicle that is based on one of the networks we investigated makes a reasonable change - such as zooming in or out - this will cause the vehicle to become confused. For example, it will not recognize traffic signs or will recognize them only at a certain point in time. Therefore, our goal today is to understand how the networks can be developed and promoted so that they decode visual information accurately, similar to the human eye."

Life itself:

Yair Weiss is a professor of computer science, lives in Jerusalem, is married and has four children (ages 10, 15, 17.5 and 20). In addition to being a researcher, he is a consultant to the technology company Mobileye and the owner of a football team - Hapoel (Katmon) Jerusalem.

More of the topic in Hayadan:

• The learning machines
• The neural networks reach a consensus
• "The deep neural networks will be in the 21st century what electricity was in the 20th century"
• "Science" reveals: Technion researchers discovered for the first time how a certain gene "sculpts" neurons in the nervous system
• let there be light