Machine-learning researchers make many decisions when designing new models. They decide how many layers to include in neural networks and what weights to give inputs at each node. The result of all this human decision-making is that complex models end up being “designed by intuition” rather than systematically, says Frank Hutter, head of the machine-learning lab at the University of Freiburg in Germany.

A growing field called automated machine learning, or autoML, aims to eliminate the guesswork. The idea is to have algorithms take over the decisions that researchers currently have to make when designing models. Ultimately, these techniques could make machine learning more accessible.

This post is also available in: עברית (Hebrew)

Imagine knowing the future. Being able to predict what’s going to happen next. It feels that this concept is merely a dream, but in reality, this dream is underway. Modeling and simulation, data analytics, AI and machine learning, distributed systems, social dynamics and human behavior simulation are fast becoming the go-to tools, and their qualities could offer significant advantages for the battlespace of tomorrow.

According to army-technology.com, London-based technology provider Improbable has been working closely with the UK Ministry of Defense (MoD) since 2018 to explore the utility of synthetic environments (SEs) for tactical training and operational and strategic planning. At the core of this work is Skyral, a platform that supports an ecosystem of industry and academia enabling the fast construction of new SEs for almost any scenario using digital entities, algorithms, AI, historic and real-time data.

Researchers at Oxford University’s Department of Materials, working in collaboration with colleagues from Exeter and Munster, have developed an on-chip optical processor capable of detecting similarities in datasets up to 1,000 times faster than conventional machine learning algorithms running on electronic processors.

The new research published in Optica took its inspiration from Nobel Prize laureate Ivan Pavlov’s discovery of classical conditioning. In his experiments, Pavlov found that by providing another stimulus during feeding, such as the sound of a bell or metronome, his dogs began to link the two experiences and would salivate at the sound alone. The repeated associations of two unrelated events paired together could produce a learned response—a conditional reflex.

Co-first author Dr. James Tan You Sian, who did this work as part of his DPhil in the Department of Materials, University of Oxford, said, “Pavlovian associative learning is regarded as a basic form of learning that shapes the behavior of humans and animals—but adoption in AI systems is largely unheard of. Our research on Pavlovian learning in tandem with optical parallel processing demonstrates the exciting potential for a variety of AI tasks.”