Neural Networks Archives - Liwaiwai

Solving A Machine-Learning Mystery

MIT researchers found that massive neural network models that are similar to large language models are capable of containing smaller linear models inside their hidden layers, which the large models could train to complete a new task using simple learning algorithms. Image by Jose-Luis Olivares, MIT Large language models like OpenAI’s GPT-3 are massive neural networks that can generate human-like text, from poetry to programming code. Trained using troves of internet data, these machine-learning models take a small bit of input text and then predict the text that is likely to come next. But that’s not all these models can do. Researchers…

Artificial Intelligence

AI Says Dino Footprints Don’t Belong To A Predator

Prehistoric footprints attributed to a vicious dinosaur predator are actually from a timid herbivore, artificial intelligence indicates. University of Queensland paleontologist Anthony Romilio used AI pattern recognition to re-analyze footprints from the Dinosaur Stampede National Monument, south-west of Winton in Central Queensland. “Large dinosaur footprints were first discovered back in the 1970s at a track site called the Dinosaur Stampede National Monument, and for many years they were believed to be left by a predatory dinosaur, like Australovenator, with legs nearly two meters long,” says Romilio. “The mysterious tracks were thought to be left during the mid-Cretaceous Period, around 93 million years ago. But working…

Self-Taught AI May Have a Lot in Common With the Human Brain

Neural networks can use self-supervised learning to figure out what matters. This process might be what helps humans do the same. FOR A DECADE now, many of the most impressive artificial intelligence systems have been taught using a huge inventory of labeled data. An image might be labeled “tabby cat” or “tiger cat,” for example, to “train” an artificial neural network to correctly distinguish a tabby from a tiger. The strategy has been both spectacularly successful and woefully deficient. Such “supervised” training requires data laboriously labeled by humans, and the neural networks often take shortcuts, learning to associate the labels with…

Why Artificial Neural Networks Have A Long Way To Go Before They Can ‘See’ Like Us

Artificial neural networks were created to imitate processes in our brains, and in many respects – such as performing the quick, complex calculations necessary to win strategic games such as chess and Go – they’ve already surpassed us. But if you’ve ever clicked through a CAPTCHA test online to prove you’re human, you know that our visual cortex still reigns supreme over its artificial imitators (for now, at least). So if schooling world chess champions has become a breeze, what’s so hard about, say, positively identifying a handwritten ‘9’? This explainer from the US YouTuber Grant Sanderson, who creates…

Internet Data Produce A Racist, Sexist Robot

A robot operating with a popular internet-based artificial intelligence system consistently gravitates to men over women, white people over people of color, and jumps to conclusions about peoples’ jobs after a glance at their face. The work is believed to be the first to show that robots loaded with an accepted and widely used model operate with significant gender and racial biases. Researchers will present a paper on the work at the 2022 Conference on Fairness, Accountability, and Transparency (ACM FAccT). “The robot has learned toxic stereotypes through these flawed neural network models,” says author Andrew Hundt, a postdoctoral fellow at Georgia…

How Machine Learning Can Support Historians Decipher Ancient Inscriptions

The origins of ancient inscriptions are often shrouded in mystery. Writing carved into stone millennia ago can be hard to read and is often missing entire sections of the text. Now a neural network, trained on thousands of existing inscriptions, could help historians figure out when and where a piece of writing comes from – as well as fill in missing words and characters. Ancient stone inscriptions offer some of the most powerful primary sources available to historians. However, as these stones are often many thousands of years old, and thus eroded, chipped or otherwise compromised, they can also be…

Developing Countries Are Being Left Behind In The AI Race – And That’s A Problem For All Of Us

Artificial Intelligence (AI) is much more than just a buzzword nowadays. It powers facial recognition in smartphones and computers, translation between foreign languages, systems which filter spam emails and identify toxic content on social media, and can even detect cancerous tumours. These examples, along with countless other existing and emerging applications of AI, help make people’s daily lives easier, especially in the developed world. As of October 2021, 44 countries were reported to have their own national AI strategic plans, showing their willingness to forge ahead in the global AI race. These include emerging economies like China and India, which…

Can Machine-Learning Models Overcome Biased Datasets?

Artificial intelligence systems may be able to complete tasks quickly, but that doesn’t mean they always do so fairly. If the datasets used to train machine-learning models contain biased data, it is likely the system could exhibit that same bias when it makes decisions in practice. For instance, if a dataset contains mostly images of white men, then a facial-recognition model trained with these data may be less accurate for women or people with different skin tones. A group of researchers at MIT, in collaboration with researchers at Harvard University and Fujitsu Ltd., sought to understand when and how a…

Artificial Intelligence

Artificial Networks Learn To Smell Like The Brain

Using machine learning, a computer model can teach itself to smell in just a few minutes. When it does, researchers have found, it builds a neural network that closely mimics the olfactory circuits that animal brains use to process odors. Animals from fruit flies to humans all use essentially the same strategy to process olfactory information in the brain. But neuroscientists who trained an artificial neural network to take on a simple odor classification task were surprised to see it replicate biology’s strategy so faithfully. “The algorithm we use has no resemblance to the actual process of evolution,” says Guangyu Robert Yang, an…

What are Adversarial AI Attacks and How Do We Combat Them?

Deep learning is the main force behind the recent advances in the field of artificial intelligence (AI). Deep learning models are capable of performing on par with, if not exceeding, human levels, at a variety of different tasks and objectives. However, deep neural networks are vulnerable to subtle adversarial perturbations applied to their inputs – adversarial AI. These adversarial perturbations, which can be imperceptible to the human eye, can easily mislead a trained deep neural network into making wrong decisions. The field of adversarial machine learning focuses on addressing this problem by developing high-performing deep learning models that are also…

Input your search keywords and press Enter.