Because navigation produces readily observable actions, it provides an important window into how perception and reasoning support intelligent behavior. This paper summarizes recent results in navigation from the perspectives of cognitive neuroscience, cognitive psychology, and cognitive robotics. Together they argue for the significance of a learned spatial cognitive model. The feasibility of such a model for navigation is demonstrated, and important issues raised for a standard model of the mind.

For centuries, scientists who have dedicated their lives to studying the human brain have attempted to unlock its mysteries. The role the brain plays in human personality -- as well as the myriad of disorders and conditions that come along with it -- is often difficult to study because studying the organ while it's still functioning in a human body is complicated. Now, researchers at The Allen Institute for Brain Science have introduced a new tool that could make such study a whole lot easier: functioning virtual brain cells. The fully 3D computer models of living human brain tissue are based on actual brain samples that were left over after surgery, and present what could be the most powerful testbed for studying the human brain ever created. The samples used to construct the virtual models was healthy tissue that was removed during brain operations, and represents parts of the brain that are typically associated with thoughts and consciousness, as well as memory.

The human brain is capable of incredible things, but it's also extremely flawed at times. Science has shown that we tend to make all sorts of mental mistakes, called "cognitive biases", that can affect both our thinking and actions. These biases can lead to us extrapolating information from the wrong sources, seeking to confirm existing beliefs, or failing to remember events the way they actually happened! To be sure, this is all part of being human – but such cognitive biases can also have a profound effect on our endeavors, investments, and life in general. For this reason, today's infographic from DesignHacks.co is particularly handy.

The Digital Human League, for example, recently unveiled'Digital Mike' – an artificial likeness of producer Mike Seymour. The idea, Digital Mike explains in a promo video, is'to produce a virtual human, and not only a virtual human, but one rendered in real time – puppeteered or driven in real time, rendered in real time, and not only that, at 90 frames per second, in stereo, in VR.' In a new study, researchers from Oxford University's Future of Humanity Institute, Yale University, and AI Impacts surveyed 352 machine learning experts to forecast the progress of AI in the next few decades. The idea, Digital Mike explains in a promo video, is'to produce a virtual human, and not only a virtual human, but one rendered in real time – puppeteered or driven in real time, rendered in real time, and not only that, at 90 frames per second, in stereo, in VR' A study from Oxford University's Future of Humanity Institute, Yale University, and AI Impacts released this past spring concluded that in less than 50 years, AI will beat humans at everything from language translation and truck driving to writing high-school essays.

Originally posted on The Horizons Tracker. I've written a few times recently about the initial forays of IBM's Watson into retail. For instance, at the back end of last year they launched Watson Trend to help us buy the perfect holiday gift, whilst they've also powered the recommendation engine at retailers such as North Face. Both are good examples of the use of AI to help provide more accurate predictions of the things we prefer. A good example of the work being undertaken in this area comes from a recently published paper that sees researchers develop a filtering model to do this job.

Deep neural networks (DNNs) have achieved unprecedented performance on a wide range of complex tasks, rapidly outpacing our understanding of the nature of their solutions. This has caused a recent surge of interest in methods for rendering modern neural systems more interpretable. In this work, we propose to address the interpretability problem in modern DNNs using the rich history of problem descriptions, theories and experimental methods developed by cognitive psychologists to study the human mind. To explore the potential value of these tools, we chose a well-established analysis from developmental psychology that explains how children learn word labels for objects, and applied that analysis to DNNs. Using datasets of stimuli inspired by the original cognitive psychology experiments, we find that state-of-the-art one shot learning models trained on ImageNet exhibit a similar bias to that observed in humans: they prefer to categorize objects according to shape rather than color. The magnitude of this shape bias varies greatly among architecturally identical, but differently seeded models, and even fluctuates within seeds throughout training, despite nearly equivalent classification performance. These results demonstrate the capability of tools from cognitive psychology for exposing hidden computational properties of DNNs, while concurrently providing us with a computational model for human word learning.

Wanted: 10,000 New Yorkers interested in advancing science by sharing a trove of personal information, from cellphone locations and credit-card swipes to blood samples and life-changing events. Researchers are gearing up to start recruiting participants from across the city next year for a study so sweeping it's called'The Human Project .' It aims to channel different data streams into a river of insight on health, aging, education and many other aspects of human life. Pictured are people walking inside the Oculus, the new transit station at the World Trade Center in New York. Researchers are gearing up to start recruiting 10,000 New Yorkers early next year for a study so sweeping it's called'The Human Project' 'That's what we're all about: putting the holistic picture together,' says project director Dr Paul Glimcher, a New York University neural science, economics and psychology professor.

In this Thursday, June 15, 2017, photo, people walk inside the Oculus, the new transit station at the World Trade Center Thursday, June 15, 2017, in New York. Researchers are gearing up to start recruiting 10,000 New Yorkers early next year for a study so sweeping it's called "The Human Project." They'll be asked to share a trove of personal information, from cellphone locations and credit-card swipes to blood samples and life-changing events.

Machine learning is on the rise due to the technological convergence of the growth of big data, decreasing data storage costs, increasing computing power, improved artificial intelligence algorithms and acceleration of cloud computing. Machine learning is the ability for computers to learn without explicit programming. It's analogous to the human ability to identify an octopus based on the set of data input that goes to the brain, such as eight arms, tentacles, lack of skeleton and other characteristics, without having prior knowledge of every type of cephalopod mollusk in existence. However, human decision-making is subject to numerous cognitive biases that can easily distort judgement. For example, iconoclastic author Tom Peters highlights 159 cognitive biases that impact management decision-making (Peters, Tom.

By their own admission, Jack Ma is uncomfortable with Artificial Intelligence (AI) and Elon Musk is scared. But why? Contrary to popular perception AI is old. To be precise it's 51-years old, widely acknowledged to have been born at a conference at Dartmouth College in 1956. That conference was attended by a diverse group of people. Three of them presented the Logic Theorist, the world's first true artificial intelligence programme. Two of them were Allen Newell and Herbert Simon.