Memories are shadows of the past but also flashlights for the future. Our recollections guide us through the world, tune our attention, and shape what we learn later in life. Human and animal studies have shown that memories can alter our perceptions of future events and the attention we give them. "We know that past experience changes stuff," said Loren Frank, a neuroscientist at the University of California, San Francisco. "How exactly that happens isn't always clear."

Palette.fm is an AI tool that can automatically add color to your old black-and-white photos or give your artwork a unique twist. It is powered by a deep learning model that analyzes and classifies images, making initial guesses for the colors that objects in the photo or illustration should be. From there, it refines those guesses and produces a highly realistic colorized image. You can further refine the colors with a written caption. It uses a simple and user-friendly interface, where you can upload your black and white photo and let the tool work its magic.

The human mind can get really complicated at times. That's when we turn to meditation, taking deep breaths to forget all the chaos. It gives us certain fulfilment--by bringing out new traits of understanding and empathy--sometimes by not doing anything at all. What if machines could also meditate or do nothing for a day or two--to learn better? As absurd as it may sound, a group of researchers have now discovered how artificial neural networks can mimic sleep patterns of the human brain, boosting their utility across a spectrum of research areas.

"The brain is very busy when we sleep, repeating what we have learned during the day," said Maxim Bazhenov, PhD, professor of medicine and a sleep researcher at University of California San Diego School of Medicine. "Sleep helps reorganize memories and presents them in the most efficient way." In previous published work, Bazhenov and colleagues have reported how sleep builds rational memory, the ability to remember arbitrary or indirect associations between objects, people or events, and protects against forgetting old memories. Artificial neural networks leverage the architecture of the human brain to improve numerous technologies and systems, from basic science and medicine to finance and social media. In some ways, they have achieved superhuman performance, such as computational speed, but they fail in one key aspect: When artificial neural networks learn sequentially, new information overwrites previous information, a phenomenon called catastrophic forgetting.

Although we don't know how brain functions yet, we have the feeling that it must have a logic unit and a memory unit. We make decisions by reasoning and by experience. So do computers, we have the logic units, CPUs and GPUs and we also have memories. But when you look at a neural network, it functions like a black box. You feed in some inputs from one side, you receive some outputs from the other side.

Although we don't know how brain functions yet, we have the feeling that it must have a logic unit and a memory unit. We make decisions by reasoning and by experience. So do computers, we have the logic units, CPUs and GPUs and we also have memories. But when you look at a neural network, it functions like a black box. You feed in some inputs from one side, you receive some outputs from the other side.