Computational models of visual attention are at the crossroad of disciplines like cognitive science, computational neuroscience, and computer vision. This paper proposes a model of attentional scanpath that is based on the principle that there are foundational laws that drive the emergence of visual attention. We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics.

Your inner monologue may be less constant than you think--more like a fridge light that turns on when you look. Thinking doesn't always involve words. Breakthroughs, discoveries, and DIY tips sent six days a week. When I first started researching this story, I assumed I was writing about other people: those fascinating outliers who reportedly lack an internal monologue--the experience of actively speaking words in your mind as a sort of private narration of your life. Then I got on a Zoom call with Dr. Russell Hurlburt, a psychologist at the University of Nevada, Las Vegas, who has spent 50 years studying inner experience, and somewhere in the first ten minutes, I started to wonder: What if I'm talking about myself?

Aqara's Matter-compatible camera promises easier smart home integration The company says it's the first Matter-certified camera. Smart home company Aqara has launched what it says is the first camera certified for Matter, the open source standard that enables interoperability across brands, like Google and Amazon. The Aqara G350 is an indoor security cam that also functions as a Zigbee and Matter hub in the Aqara Home app, which means the camera will enable you to control various devices across smart home protocols from different brands within one location. The camera itself comes with a 4K wide-angle and a 2.5K telephoto lens, providing both panoramic and closeup views. It also has 9x hybrid zoom and a pan-tilt mechanism that can give you 360-degree coverage of the room it's in.

One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network. While this approach works well in many domains, in domains where the optimal value function cannot easily be reduced to a low-dimensional representation, learning can be very slow and unstable. This paper contributes towards tackling such challenging domains, by proposing a new method, called Hybrid Reward Architecture (HRA). HRA takes as input a decomposed reward function and learns a separate value function for each component reward function. Because each component typically only depends on a subset of all features, the corresponding value function can be approximated more easily by a low-dimensional representation, enabling more effective learning. We demonstrate HRA on a toy-problem and the Atari game Ms. Pac-Man, where HRA achieves above-human performance.

Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting. Although simply replaying all previous data alleviates the problem, it requires large memory and even worse, often infeasible in real world applications where the access to past data is limited. Inspired by the generative nature of the hippocampus as a short-term memory system in primate brain, we propose the Deep Generative Replay, a novel framework with a cooperative dual model architecture consisting of a deep generative model ("generator") and a task solving model ("solver"). With only these two models, training data for previous tasks can easily be sampled and interleaved with those for a new task. We test our methods in several sequential learning settings involving image classification tasks.

Plus: China has approved the world's first commercial brain chip. Where OpenAI's technology could show up in Iran OpenAI has controversially agreed to give the Pentagon access to its AI. But where exactly could its tech show up, and which applications will its customers and employees tolerate? There's pressure to integrate it quickly with existing military tools. One defense official revealed it could even assist in selecting strike targets. OpenAI's partnership with Anduril, which makes drones and counter-drone technologies, adds another hint at what is to come.

Navy robots from Gecko Robotics will inspect U.S. warships in $71 million effort to reduce maintenance delays as only 60% of fleet remains operational amid China's naval expansion.

Whole-brain neural connectivity data are now available from viral tracing experiments, which reveal the connections between a source injection site and elsewhere in the brain.

Although text-to-image generation is rapidly advancing, these AI models are mostly English-centric. Researchers at the University of Amsterdam Faculty of Science have created NeoBabel, an AI image generator that can work in six different languages. By making all elements of their research open source, anyone can build on the model and help push inclusive AI research. When you generate an image with AI, the results are often better when your prompt is in English. This is because many AI models are English at their core: if you use another language, your prompt is translated into English before the image is created.

The goal of minimizing misclassification error on a training set is often just one of several real-world goals that might be defined on different datasets. For example, one may require a classifier to also make positive predictions at some specified rate for some subpopulation (fairness), or to achieve a specified empirical recall. Other real-world goals include reducing churn with respect to a previously deployed model, or stabilizing online training. In this paper we propose handling multiple goals on multiple datasets by training with dataset constraints, using the ramp penalty to accurately quantify costs, and present an efficient algorithm to approximately optimize the resulting non-convex constrained optimization problem. Experiments on both benchmark and real-world industry datasets demonstrate the effectiveness of our approach.