Month: September 2022

ARCHITECTURE. "We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples." (Google Deepmind). https://lnkd.in/dqC_7Tc View in LinkedIn

NOT PRE-PROGRAMMED. "As opposed to other AIs, such as IBM's Deep Blue or Watson, which were developed for a pre-defined purpose and only function within its scope, DeepMind claims that their system is not pre-programmed: it learns from experience, using only raw pixels as data input." https://lnkd.in/dRxFGp6 View in LinkedIn

HUMAN PARITY. “We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters." https://lnkd.in/daWaSDk View in LinkedIn

ULTIMATE CHALLENGE. “Go has always been the pinnacle of perfect information games. It’s way more complicated than chess in terms of possibility, so it’s always been a bit of a holy grail or grand challenge for AI research, especially since Deep Blue.” https://lnkd.in/dT88xiV View in LinkedIn

OLYMPIC. “I think for perfect information games, Go is the pinnacle.” https://lnkd.in/dT88xiV View in LinkedIn

MACHINE INTUITION. “Monte Carlo tree search was a big innovation ten years ago, but I think what we’ve done with AlphaGo is introduce with the neural networks this aspect of intuition, if you want to call it that, and that’s really the thing that separates out top Go players: their intuition.” https://lnkd.in/dT88xiV View in LinkedIn

CHAMPION. “DeepMind’s stunning victories over Go legend Lee Se-dol have stoked excitement over artificial intelligence’s potential more than any event in recent memory. But the Google subsidiary’s AlphaGo program is far from its only project — it’s not even the main one.” https://lnkd.in/dT88xiV View in LinkedIn

AHEAD OF THE CURVE. “Let us all raise a glass to AlphaGo and mark another big moment in the advance of artificial intelligence and then perhaps start to worry. AlphaGo, Google DeepMind’s game of Go-playing AI just bested the best Go-playing human currently alive, the renowned Lee Sedol. This was not supposed to happen. At least, not for a while. An artificial intelligence capable of beating the best humans at the game was predicted to be 10 years away.” https://lnkd.in/dyZMbSC View in LinkedIn

FRAGMENT FROM NATURE continues from last weekend and concludes this weekend on the linguistic perspective on contextual genetics and the controversial idea of the significant impact of mobile genetic elements on evolution, from an essay by Günther Witzany. Biologists as a group tend to fiercely resist new ideas and be locked into arcane outmoded ideas, and the poor acceptance of the enormous impact of mobile genetic elements on evolution is a poster-child example, not to mention the truly Luddite proposition that these kinds of elements (and viruses) are not alive, simply because they stuck to wrong definitions of life. View in LinkedIn

TWO WAY READING. “The change from a read-only-memory genome with copying errors to a read-and-write genome with active change operators is fundamental.” https://lnkd.in/dWwkKpD View in LinkedIn