Korea Advanced Institute of Science and Technology

Samsung Electronics Co., Ltd.

Sungju Hwang

Eunho Yang

Seungwoo Seo

Gunhee Kim

Jinwoo Shin

Youyoung Song

Juyong Kim

Jaehong Yoon

Yookoon Park

Jeongtae Lee

Donghyun Na

Haebum Lee

A method of training a retrosynthesis prediction model includes determining first attention information from first character string information of a product, based on first graph information of the product, encoding the first character string information, based on the determined first attention information, and determining second attention information from the first graph information and second graph information of a reactant. The method further includes decoding second character string information of the reactant, based on the determined second attention information, and training the retrosynthesis prediction model, based on the decoded second character string information.

Method and apparatus for training retrosynthesis prediction model

A method for re-learning a trained model is provided. The method for re-learning a trained model includes: receiving a data set including the trained model consisting of a plurality of neurons and a new task; identifying a neuron associated with the new task among the plurality of neurons to selectively re-learn a parameter associated with the new task for the identified neuron; and dynamically expanding a size of the trained model on which the selective re-learning is performed if the trained model on which the selective re-learning has a preset loss value to reconstruct the input trained model.

Electronic apparatus and method for re-learning trained model

A method for generating a trained model is provided. The method for generating a trained model includes: receiving a learning data; generating an asymmetric multi-task feature network including a parameter matrix of the trained model which permits an asymmetric knowledge transfer between tasks and a feedback matrix for a feedback connection from the tasks to features; computing a parameter matrix of the asymmetric multi-task feature network using the input learning data to minimize a predetermined objective function; and generating an asymmetric multi-task feature trained model using the computed parameter matrix as the parameter of the generated asymmetric multi-task feature network.

Electronic apparatus and method for generating trained model

An electronic apparatus is provided. The electronic apparatus includes: a memory storing a trained model including a plurality of layers; and a processor initializing a parameter matrix and a plurality of split variables of a trained model, calculating a new parameter matrix having a block-diagonal matrix for the plurality of split variables and the trained model to minimize a loss function for the trained model, a weight decay regularization term, and an objective function including a split regularization term defined by the parameter matrix and the plurality of split variables, vertically splitting the plurality of layers according to the group based on the computed split parameters and reconstruct the trained model using the computed new parameter matrix as parameters of the vertically split layers.

Electronic apparatus and method for optimizing trained model

Growing community of inventors

Daejeon, South Korea

Sungju Hwang