公开(公告)号：US20230033000A1

公开(公告)日：2023-02-02

申请号：US17887745

申请日：2022-08-15

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/04 ,  G06N3/08 ,  G06F3/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US20220172055A1

公开(公告)日：2022-06-02

申请号：US17601105

申请日：2020-04-10

Applicant: Google LLC

Inventor： Maxwell Bileschi ,  Lucy Colwell ,  Theodore Sanderson ,  David Benjamin Belanger ,  Jamie Alexander Smith ,  Drew Bryant ,  Mark Andrew DePristo ,  Brandon Carter

IPC: G06N3/08 ,  G16B40/00 ,  G16B50/10 ,  G16B20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting biological functions of proteins. In one aspect, a method comprises: obtaining data defining a sequence of amino acids in a protein; processing the data defining the sequence of amino acids in the protein using a neural network, wherein: the neural network is a convolutional neural network comprising one or more dilated convolutional layers; and the neural network is configured to process the data defining the sequence of amino acids in the protein in accordance with trained parameter values of the neural network to generate a neural network output characterizing at least one predicted biological function of the sequence of amino acids in the protein; and identifying the predicted biological function of the sequence of amino acids in the protein using the neural network output.

公开(公告)号：US12175351B2

公开(公告)日：2024-12-24

申请号：US15994144

申请日：2018-05-31

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Parthasarathy Ranganathan ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06N3/047 ,  G06N3/063 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for pre-fetching data from memory using neural networks. One example system receives a sequence of prior program counter addresses of a computer program and corresponding delta values. The system creates an input representation based on the sequence. The system provides the input representation as input to a recurrent neural network. The system receives from the recurrent neural network an output that defines a probability distribution over future delta values. Each probability in the distribution represents a likelihood that execution of a future instruction of the computer program will cause data to be fetched from a particular future memory address.

公开(公告)号：US12033056B2

公开(公告)日：2024-07-09

申请号：US17887745

申请日：2022-08-15

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06F3/06 ,  G06N3/08

CPC classification number: G06N3/044 ,  G06F3/0604 ,  G06F3/0659 ,  G06F3/0673 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US20250005322A1

公开(公告)日：2025-01-02

申请号：US18737119

申请日：2024-06-07

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06F3/06 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US11416733B2

公开(公告)日：2022-08-16

申请号：US16262785

申请日：2019-01-30

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/04 ,  G06N3/08 ,  G06F3/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US20200160150A1

公开(公告)日：2020-05-21

申请号：US16262785

申请日：2019-01-30

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/04 ,  G06N3/08 ,  G06F3/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.