Lifeboat Foundation

Deep neural networks have achieved highly promising results on several tasks, including image and text classification. Nonetheless, many of these computational methods are prone to what is known as catastrophic forgetting, which essentially means that when they are trained on a new task, they tend to rapidly forget how to complete tasks they were trained to complete in the past.

Researchers at Université Paris-Saclay-CNRS recently introduced a new technique to alleviate forgetting in binarized neural networks. This technique, presented in a paper published in Nature Communications, is inspired by the idea of synaptic metaplasticity, the process through which synapses (junctions between two nerve cells) adapt and change over time in response to experiences.

“My group had been working on binarized neural networks for a few years,” Damien Querlioz, one of the researchers who carried out the study, told TechXplore. “These are a highly simplified form of deep neural networks, the flagship method of modern artificial intelligence, which can perform complex tasks with reduced memory requirements and energy consumption. In parallel, Axel, then a first-year Ph.D. student in our group, started to work on the synaptic metaplasticity models introduced in 2005 by Stefano Fusi.”

There may be life in Enceladus’ deep sea plumes.

The Cassini probe revealed a subsurface ocean beneath Enceladus’ icy surface that may be habitable. A new analysis shows that the chemistry has the right stuff.

Calico has made some important discoveries about Yamanaka factors.

In a preprint paper, scientists from Calico, Google’s longevity research behemoth, suggest that contrary to our previous understanding, transient reprogramming of cells using Yamanaka factors involves suppressing cellular identity, which may open the door to carcinogenic mutations. They also propose a milder reprogramming method inspired by limb regeneration in amphibians [1].

Rejuvenation that can give you cancer

Continue reading “Calico Scientists Develop Safer Cellular Reprogramming” »

Analog AI processor company Mythic launched its M1076 Analog Matrix Processor today to provide low-power AI processing.

The company uses analog circuits rather than digital to create its processor, making it easier to integrate memory into the processor and operate its device with 10 times less power than a typical system-on-chip or graphics processing unit (GPU).

The M1076 AMP can support up to 25 trillion operations per second (TOPS) of AI compute in a 3-watt power envelope. It is targeted at AI at the edge applications, but the company said it can scale from the edge to server applications, addressing multiple vertical markets including smart cities, industrial applications, enterprise applications, and consumer devices.

“I didn’t think I would be emotional about this.”

It’s not just humans that use prosthetic limbs—wounded or disabled animals can benefit from them, too. In the past, we’ve reported on cats, dogs, and even an elephant who have been fitted for prosthesis. The latest creature who’s now learning to walk on an artificial foot is an adorable duck named Waddles.

Waddles was born with a deformed leg, but his adoptive owner Ben Weinman wanted to help him live a better life. He contacted Derrick Campana, a Certified Pet Prostheticist at Bionic Pets who made a 3D-printed prosthetic leg and foot.

Continue reading “Waddles the Disabled Duck Walks for the First Time on His 3D-Printed Prosthetic Leg” »

Discovery in Salamanders by James W. Godwin, Ph.D., brings science closer to the development of regenerative medicine therapies.

Many salamanders can readily regenerate a lost limb, but adult mammals, including humans, cannot. Why this is the case is a scientific mystery that has fascinated observers of the natural world for thousands of years.

Now, a team of scientists led by James Godwin, Ph.D., of the MDI Biological Laboratory in Bar Harbor, Maine, has come a step closer to unraveling that mystery with the discovery of differences in molecular signaling that promote regeneration in the axolotl, a highly regenerative salamander, while blocking it in the adult mouse, which is a mammal with limited regenerative ability.

Last Tuesday, teams from Google and Harvard published an intricate map of every cell and connection in a cubic millimeter of the human brain.

The mapped region encompasses the various layers and cell types of the cerebral cortex, a region of brain tissue associated with higher-level cognition, such as thinking, planning, and language. According to Google, it’s the largest brain map at this level of detail to date, and it’s freely available to scientists (and the rest of us) online. (Really. Go here. Take a stroll.)

“The human brain is an immensely complex network of brain cells which is responsible for all human behavior, but until now, we haven’t been able to completely map these connections within even a small region of the brain,” said Dr. Alexander Shapson-Coe, a postdoctoral fellow at Harvard’s Lichtman Lab and lead author of a preprint paper about the work.

Designing an autonomous, learning smart garden.

In the first episode of Build Out, Colt and Reto — tasked with designing the architecture for a “Smart Garden” — supplied two very different concepts, that nevertheless featured many overlapping elements. Take a look at the video to see what they came up with, then continue reading to see how you can learn from their explorations to build your very own Smart Garden.

Both solutions aim to optimize plant care using sensors, weather forecasts, and machine learning. Watering and fertilizing routines for the plants are updated regularly to guarantee the best growth, health, and fruit yield possible.

Continue reading “Building a Garden that Cares for Itself” »

https://youtube.com/watch?v=BuY3kLfxtaY

This is an automatic hydroponics system that also has scaleable farms that use 95 percent less water.

Grow fresh herbs, vegetables, and more in 3 easy steps all year round with AeroGarden indoor garden systems. No soil, no sun, & no green thumb required!