Lifeboat Foundation

Another well-known method for physical learning is Equilibrium Propagation (EP), sharing similar procedure with coupled learning and being able to define the arbitrary differentiable loss function³². This method has been demonstrated in various physical systems, numerically in nonlinear resistor networks³³ and coupled phase oscillators³⁴, experimentally on Ising machines³⁵.

So far, the MNNs based on the physical learning have been developed using the platform of origami structures^28,36 and disordered networks^29,37 to demonstrate machine learning through simulations. The experimental proposals involve using directed springs with variable stiffness³⁸ and manually adjusting the rest length of springs³¹.

Here, we present a highly-efficient training protocol for MNNs through mechanical analogue of in situ backpropagation, derived from the adjoint variable method, in which theoretically the exact gradient can be obtained from only the local information. By using 3D-printed MNNs, we demonstrate the feasibility of obtaining the gradient of the loss function experimentally solely from the bond elongation of MNNs in only two steps, using local rules, with high accuracy. Besides, leveraging the obtained gradient, we showcase the successful training in simulations of a mechanical network for behaviors learning and various machine learning tasks, achieving high accuracy in both regression and Iris flower classification tasks. The trained MNNs are then validated both numerically and experimentally. In addition, we illustrate the retrainability of MNNs after switching tasks and damage, a feature that may inspire further inquiry into more robust and resilient design of MNNs.

The latest weather forecasting AI model from Google DeepMind can beat the leading providers more than 97 per cent of the time, and it is quicker and cheaper to run.

By Matthew Sparkes

Users of the healthcare app Alan whose queries were answered by a medical AI reported high satisfaction levels, but one exchange included “potentially dangerous inaccuracies”

Recent developments in AI and neurological research may prompt concern. However, placing outright bans on such research is unlikely to be the best solution — and may hold us back.

In August, the Food and Drug Administration (FDA) granted accelerated approval of Tecelra (afamitresgene autoleucel)— the first T-cell receptor therapy for solid tumors—for people with inoperable or metastatic synovial sarcoma. Tecelra is a gene therapy created from a patient’s own T cells. A sample of cells is removed and genetically modified to express a natural T-cell receptor that targets MAGE-A4, an antigen expressed on cancer cells. In the Phase II SPEARHEAD-1 trial, the overall response rate was 43%, and 39% of responders were still doing well a year later.

The asteroid that extinguished the dinosaurs is estimated to have been about 10 kilometers across. That’s about as wide as Brooklyn, New York. Such a massive impactor is predicted to hit Earth rarely, once every 100 million to 500 million years.

In contrast, much smaller asteroids, about the size of a bus, can strike Earth more frequently, every few years. These “decameter” asteroids, measuring just tens of meters across, are more likely to escape the main asteroid belt and migrate in to become near-Earth objects. If they make impact, these small but mighty space rocks can send shockwaves through entire regions, such as the 1908 impact in Tunguska, Siberia, and the 2013 asteroid that broke up in the sky over Chelyabinsk, Urals. Being able to observe decameter main-belt asteroids would provide a window into the origin of meteorites.

The team’s detection method, which identified 138 space rocks ranging from bus-to stadium-sized, could aid in tracking potential asteroid impactors.

Continue reading “MIT astronomers find the smallest asteroids ever detected in the main belt” »

Twitter co-founder Jack Dorsey arrives in Kenya.

Intel Foundry has showcased “breakthrough” developments in the realm of transistor and packaging technologies, revealing material and silicon innovation.

Intel Foundry Showcases “Subtractive Ruthenium” & New Transistor Technologies To Ensure Node Scalability

[Press Release]: Today at the IEEE International Electron Devices Meeting (IEDM) 2024, Intel Foundry unveiled breakthroughs to help drive the semiconductor industry forward into the next decade and beyond. Intel Foundry showcased new material advancements that help improve interconnections within a chip, resulting in up to 25% capacitance by using subtractive ruthenium.

The latest AI news, analysis, and insight from VentureBeat, the most authoritative source on transformative technology.