US Patent Issued to DeepMind Technologies on June 17 for "Learning abstractions using patterns of activations of a neural network hidden layer" (British Inventors)

ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,435, issued on June 17, was assigned to DeepMind Technologies Ltd. (London).

"Learning abstractions using patterns of activations of a neural network hidden layer" was invented by Alexander Lerchner (London) and Demis Hassabis (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "We describe an artificial neural network comprising: an input layer of input neurons, one or more hidden layers of neurons in successive layers of neurons above the input layer, and at least one further, concept-identifying layer of neurons above the hidden layers. The neural network includes an activation memory coupled to an intermediate, hidden layer of neurons between ...