International Business Machines Corporation

Zhi Qiao

Jing Li

Guo Tong Xie

Shi Wan Zhao

Hai Feng Liu

Shi Jing Guo

Li Ni Zhang

Zhong Su

Zhi Hu Wang

Shiwan Zhao

Jing Mei

Techniques for identifying representative patients from a patient group are provided. Based on an outcome of interest, one or more patients can be grouped according to phenotyping features associated with the outcome of interest. Additionally, in response to grouping the one or more patients, a representative patient of the one or more patients can be determined based on values associated with the phenotyping features.

Neural network based selection of representative patients

A dataset regarding a plurality of applications is obtained. A set of parameters is determined from the dataset, comprising at least a sample performance trajectory, a risk factor, and a performance outcome. A maximum likelihood of each performance outcome is determined using a likelihood function, the likelihood function being a mixture model of a trajectory model and an outcome model. The set of parameters is updated according to the maximum likelihood of each performance outcome. A performance trajectory model is built according to the updated set of parameters. The plurality of applications is then grouped into subgroups according to the performance trajectory model, each subgroup containing one or more applications, and each of the one or more applications in a given subgroup having a same or similar trajectory to each other. An alert associated with the applications in at least one of subgroups may be generated.

Outcome-driven trajectory tracking

A computer-implemented method for implementing separated attention on like and dislike items for personalized ranking includes performing an element-wise product on a user embedding and a final like item embedding to generate a first vector. The method further includes performing an element-wise product on the user embedding and a final dislike item embedding to generate a second vector. The method further includes computing a probability that the user prefers the like item to the dislike item based on the first and second vectors, and generating one or more item recommendations including one or more electronic images for the user using the probability.

Recommendation systems implementing separated attention on like and dislike items for personalized ranking

A method and system of imputing corrupted sequential data is provided. A plurality of input data vectors of a sequential data is received. For each input data vector of the sequential data, the input data vector is corrupted. The corrupted input data vector is mapped to a staging hidden layer to create a staging vector. The input data vector is reconstructed based on the staging vector, to provide an output data vector. adjusted parameter of the staging hidden layer is iteratively trained until it is within a predetermined tolerance of a loss function. A next input data vector of the sequential data is predicted based on the staging vector. The predicted next input data vector is stored.

Missing values imputation of sequential data

Growing community of inventors

Beijing, China

Zhi Qiao