Abstract: Approaches to zero-shot learning include partitioning training data into first and second sets according to classes assigned to the training data, training a prediction module based on the first set to predict a cluster center based on a class label, training a correction module based on the second set and each of the class labels in the first set to generate a correction to a cluster center predicted by the prediction module, presenting a new class label for a new class to the prediction module to predict a new cluster center, presenting the new class label, the predicted new cluster center, and each of the class labels in the first set to the correction module to generate a correction for the predicted new cluster center, augmenting a classifier based on the corrected cluster center for the new class, and classifying input data into the new class using the classifier.

Abstract: The disclosure relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, L2, A, B, R1, R2, R3, and R4 are described herein.

Abstract: The invention relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, A, X1, X2, R1, R2, and R3 are described herein.

Abstract: Approaches to zero-shot learning include partitioning training data into first and second sets according to classes assigned to the training data, training a prediction module based on the first set to predict a cluster center based on a class label, training a correction module based on the second set and each of the class labels in the first set to generate a correction to a cluster center predicted by the prediction module, presenting a new class label for a new class to the prediction module to predict a new cluster center, presenting the new class label, the predicted new cluster center, and each of the class labels in the first set to the correction module to generate a correction for the predicted new cluster center, augmenting a classifier based on the corrected cluster center for the new class, and classifying input data into the new class using the classifier.

Abstract: The disclosure relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, L2, A, B, R1, R2, R3, and R4 are described herein.

Abstract: The disclosure relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, L2, A, B, R1, R2, R3, and R4 are described herein.

Abstract: Approaches to zero-shot learning include partitioning training data into first and second sets according to classes assigned to the training data, training a prediction module based on the first set to predict a cluster center based on a class label, training a correction module based on the second set and each of the class labels in the first set to generate a correction to a cluster center predicted by the prediction module, presenting a new class label for a new class to the prediction module to predict a new cluster center, presenting the new class label, the predicted new cluster center, and each of the class labels in the first set to the correction module to generate a correction for the predicted new cluster center, augmenting a classifier based on the corrected cluster center for the new class, and classifying input data into the new class using the classifier.

Abstract: The invention relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, A, X1, X2, R1, R2, and R3 are described herein.

Abstract: The invention relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): (I), wherein L1, A, X1, X2, R1, R2, and R3 are described herein.

Abstract: Approaches to zero-shot learning include partitioning training data into first and second sets according to classes assigned to the training data, training a prediction module based on the first set to predict a cluster center based on a class label, training a correction module based on the second set and each of the class labels in the first set to generate a correction to a cluster center predicted by the prediction module, presenting a new class label for a new class to the prediction module to predict a new cluster center, presenting the new class label, the predicted new cluster center, and each of the class labels in the first set to the correction module to generate a correction for the predicted new cluster center, augmenting a classifier based on the corrected cluster center for the new class, and classifying input data into the new class using the classifier.

Abstract: The disclosure relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): wherein L1, L2, A, B, R1, R2, R3, and R4 are described herein.

Abstract: The invention relates to activators of FXR useful in the treatment of autoimmune disorders, liver disease, intestinal disease, kidney disease, cancer, and other diseases in which FXR plays a role, having the Formula (I): (I), wherein L1, A, X1, X2, R1, R2, and R3 are described herein.