DeepMind Technologies Limited patent applications on July 25th, 2024
Patent Applications by DeepMind Technologies Limited on July 25th, 2024
DeepMind Technologies Limited: 2 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/045 (2), G06N3/086 (1), G06F16/901 (1), G06F17/15 (1), G06N3/092 (1) G06N3/086 (1), G06N3/092 (1)
With keywords such as: neural, network, policy, level, operations, nodes, reward, input, vector, and environment in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Chrisantha Thomas Fernando of London (GB) for deepmind technologies limited, Karen Simonyan of London (GB) for deepmind technologies limited, Koray Kavukcuoglu of London (GB) for deepmind technologies limited, Hanxiao Liu of Santa Clara CA (US) for deepmind technologies limited, Oriol Vinyals of London (GB) for deepmind technologies limited
IPC Code(s): G06N3/086, G06F16/901, G06F17/15, G06N3/045
CPC Code(s): G06N3/086
Abstract: a computer-implemented method for automatically determining a neural network architecture represents a neural network architecture as a data structure defining a hierarchical set of directed acyclic graphs in multiple levels. each graph has an input, an output, and a plurality of nodes between the input and the output. at each level, a corresponding set of the nodes are connected pairwise by directed edges which indicate operations performed on outputs of one node to generate an input to another node. each level is associated with a corresponding set of operations. at a lowest level, the operations associated with each edge are selected from a set of primitive operations. the method includes repeatedly generating new sample neural network architectures, and evaluating their fitness. the modification is performed by selecting a level, selecting two nodes at that level, and modifying, removing or adding an edge between those nodes according to operations associated with lower levels of the hierarchy.
Inventor(s): Tom Ben Zion Zahavy of London (GB) for deepmind technologies limited, Brendan Timothy O'Donoghue of London (GB) for deepmind technologies limited, Guillaume Desjardins of London (GB) for deepmind technologies limited, Satinder Singh Baveja of Ann Arbor MI (US) for deepmind technologies limited
IPC Code(s): G06N3/092, G06N3/045
CPC Code(s): G06N3/092
Abstract: the actions of an agent in an environment are selected using a policy model neural network which implements a policy model defining, for any observed state of the environment characterized by an observation received by the policy model neural network, a state-action distribution over the set of possible actions the agent can perform. the policy model neural network is jointly trained with a cost model neural network which, upon receiving an observation characterizing the environment, outputs a reward vector. the reward vector comprises a corresponding reward value for every possible action. the training involves a sequence of iterations, in each of which (a) a cost model is derived based on the state-action distribution of a candidate policy model defined in one or more previous iterations, and subsequently (b) a candidate policy model is obtained based on reward vector(s) defined by the cost model obtained in the iteration.
DeepMind Technologies Limited patent applications on July 25th, 2024
