D.e. Shaw Research, LLC

Juno Online Services, Inc.

Peter Skopp

Paul Maragakis

John K Salmon

Vinod R Marur

Dharmender S Dulai

Benjamin F Vitale

James P Roney

Andreas Kraemer

Clifford Sc Tse

Hunter Nisonoff

A system is disclosed for encoding a data string of a first modality into a hierarchical tokenized representation for processing by a text-based deep neural network (DNN) trained on a second modality. The data string comprises multiple units, each having one or more attributes. Each attribute is represented in the tokenized string as a sequence of hierarchical tokens, with a first hierarchical token encoding one or more most significant bits and a subsequent hierarchical token encoding one or more less significant bits. The DNN processes the data string bidirectionally, across the sequence of units and within the token hierarchy, to select tokens that capture attribute information. The selected hierarchical tokens output by the DNN from a representation of the original data string that preserves attribute detail while enabling cross-modal processing using models trained on text.

Multi-modal hierarchical tokenization deep neural network

Discovering molecules (which may be known or may never have been cataloged or ever synthesized) that have desired characteristics is addressed using a machine learning approach. As compared to a brute-force search of a database of known molecules, which may not be computationally feasible, the present machine learning approach renders identification of both known and unknown molecules computationally tractable. Furthermore, the computational effort is largely shifted to training of the machine learning system using a database of known molecules, and the generation of molecules to match any particular characteristics requires relatively little computation. The molecules using the present approach may be further studied, for example, with computer-based simulation or after physical synthesis using biological experimentation to ultimately yield useful chemical compounds.

Molecular graph generation from structural features using an artificial neural network

A method and apparatus to determine user identity and limit access to a communications network. A first message containing user identity information is received from a client computer in accordance with a first protocol. A first network address is determined from the first message. A second message containing an information request is also received from the client in accordance with a second protocol, and a second network address is determined from the second message. The requesting user identity is then determined based on the first network address, the user identity information and the second network address. Based on the requesting user identity, it can be decided whether to grant the information request. If access is granted, the requested information is retrieved using the communications network.

Method and apparatus to determine user identity and limit access to a communications network

Growing community of inventors

New York, NY, United States of America

Peter Skopp