Never miss a story

Get subscribed to our newsletter


×
These networks have played a pivotal role in helping scientists understand how our brains perceive the things that we see. Pixabay

A team of researchers at the Centre for Neuroscience (CNS) in the Indian Institute of Science (IISc) recently conducted a study to compare the visual perception of the deep neural networks to that of humans and after conducting series of experiments they have concluded that deep neural networks visual perception are different from that of humans. According to IISc’s Associate Professor at the CNS, S.P.Arun, who led the team of researchers, said that deep neural networks are machine learning systems inspired by the network of brain cells or neurons in the human brain, which can be trained to perform specific tasks.

The team’s study published in Nature Communications, a journal, stated that deep networks, although a good model for understanding how the human brain visualizes objects, works differently from the latter.”While complex computation is trivial for them, certain tasks that are relatively easy for humans can be difficult for these networks to complete,” Arun claimed.


Follow NewsGram on Facebook to stay updated.

“These networks have played a pivotal role in helping scientists understand how our brains perceive the things that we see. Although deep networks have evolved significantly over the past decade, they are still nowhere close to performing as well as the human brain in perceiving visual cues. The team has compared various qualitative properties of these deep networks with those of the human brain,” he explained. His team studied 13 different perceptual effects and uncovered previously unknown qualitative differences between deep networks and the human brain.

Arun and his team attempted to understand which visual tasks can be performed by these networks naturally by virtue of their architecture, and which require further training”Lots of studies have been showing similarities between deep networks and brains, but no one has really looked at systematic differences,” Arun claimed, who is the senior author of the study. He added that identifying these differences can push us closer to making these networks more brain-like.

While Georgin Jacob, first author and Ph.D. student at the CNS told that deep neural networks have revolutionized computer vision, and their object representations across layers match coarsely with visual cortical areas in the brain.” However, whether these representations exhibit qualitative patterns seen in human perception or brain representations remains unresolved,” he added. Citing an example of the Thatcher effect, Arun pointed out it is a phenomenon where humans find it easier to recognize local feature changes in an upright image, but this becomes difficult when the image is flipped upside-down.


His team studied 13 different perceptual effects and uncovered previously unknown qualitative differences between deep networks and the human brain. Pixabay

“Deep networks trained to recognize upright faces showed a Thatcher effect when compared with networks trained to recognize objects. Another visual property of the human brain, called mirror confusion, was tested on these networks. To humans, mirror reflections along the vertical axis appear more similar than those along the horizontal axis. This proves that deep networks also show stronger mirror confusion for vertical compared to horizontally reflected images,” he explained.

Jacob added that another phenomenon peculiar to the human brain is that it focuses on coarser details first.”This is known as the global advantage effect. For example, in an image of a tree, our brain would first see the tree as a whole before noticing the details of the leaves in it. Similarly, when presented with an image of a face, humans first look at the face as a whole, and then focus on finer details like the eyes, nose, mouth, and so on,” he said.

He added that surprisingly, neural networks showed a local advantage which means that, unlike the brain, the networks focus on the finer details of an image first.”Therefore, even though these neural networks and the human brain carry out the same object recognition tasks, the steps followed by the two are very different.”Their study also finds that convolutional or deep neural networks have revolutionized computer vision with their human-like accuracy on object-recognition tasks, and their object representations match coarsely with the brain.


Some phenomena were present in randomly initialized networks, such as the global advantage effect, sparseness, and relative size. Pixabay

“Yet they are still outperformed by humans and show systematic finer-scale deviations from human perception. Even these differences are largely quantitative in that there are no explicit or emergent properties that are present in humans but absent in deep networks,” the study opined. According to this study, it is possible that these differences can be fixed by training deep networks on larger datasets, incorporating more constraints, or by modifying network architecture such as by including recurrence.

The team added that they recast well-known perceptual and neural phenomena in terms of distance comparisons, and ask whether they are present in feed-forward deep neural networks trained for object recognition.”Some phenomena were present in randomly initialized networks, such as the global advantage effect, sparseness, and relative size. Many others were present after object recognition training, such as the Thatcher effect, mirror confusion, Weber’s law, relative size, multiple object normalization, and correlated sparseness.

ALSO READ: Machine Learning Program To Identify Covid19 Related Conspiracy Theories

Yet other phenomena were absent in trained networks, such as 3D shape processing, surface invariance, occlusion, natural parts, and the global advantage. These findings indicate sufficient conditions for the emergence of these phenomena in brains and deep networks, and offer clues to the properties that could be incorporated to improve deep networks,” the study explained.

The study observed that deep neural networks trained on specific tasks (like scene parsing) can explain the responses in functionally specific brain regions (like the occipital place area that is known to be involved in recognizing navigational affordances) better than a deep neural network trained on a different task. The study concluded by stating that their analyses can help researchers build more robust neural networks that not only perform better but are also immune to “adversarial attacks” that aim to derail them. (IANS/JC)


Popular

Unsplash

Feminism itself is nothing but a simple movement that pursues equal rights for women (including transwomen) and against misogyny both external and internal.

"In India, to be born as a man is a crime, to question a woman is an atrocious crime, and this all because of those women who keep suppressing men in the name of feminism."

Feminism, a worldwide movement that started to establish, define and defend equal rights for women in all sections- economically, politically, and socially. India, being a patriarchal society gives a gender advantage to the men in the society thus, Indian feminists sought to fight against the culture-specific issue for women in India. Feminism itself is nothing but a simple movement that pursues equal rights for women (including transwomen) and against misogyny both external and internal. It states nowhere that women should get more wages than men, that women deserve more respect than men, that's pseudo-feminism.

Keep Reading Show less
wikimedia commons

Yakshi statue by Kanayi Kunjiraman at Malampuzha garden, Kerala

Kerala is a land of many good things. It has an abundance of nature, culture, art, and food. It is also a place of legend and myth, and is known for its popular folklore, the legend of Yakshi. This is not a popular tale outside the state, but it is common knowledge for travellers, especially those who fare through forests at night.

The legend of the yakshi is believed to be India's equivalent of the Romanian Dracula, except of course, the Yakshi is a female. Many Malayalis believe that the Yakshi wears a white saree and had long hair. She has a particular fragrance, which is believed to be the fragrance of the Indian devil-tree flowers. She seduces travellers with her beauty, and kills them brutally.

Keep Reading Show less
Pinterest

Ancient India not only made mentions of homosexuality but accepted it as well.


The LGBTQ+ acronym stands for Lesbian, Gay, Bisexual, Transgender, Queer, and others. In India LGBTQ+ community also include a specific social group, part religious cult, and part caste: the Hijras. They are culturally defined either as "neither men nor women" or as men who become women by adopting women's dress and behavior. Section 377 of the India Penal code that criminalized all sexual acts "against the order of nature" i.e. engaging in oral sex or anal sex along with other homosexual activities were against the law, ripping homosexual people off of their basic human rights. Thus, the Indian Supreme Court ruled a portion of Section 377 unconstitutional on 6th September 2018.

Keep reading... Show less