Abstract: A scheduling algorithm for scheduling training of deep neural network (DNN) weights on processing units identifies a next job to provisionally assign a processing unit (PU) based on a doubling heuristic. The doubling heuristic makes use of an estimated number of training sets needed to complete training of weights for a given job and/or a training speed function which indicates how fast the weights are converging. The scheduling algorithm solves a problem of efficiently assigning PUs when multiple DNN weight data structures must be trained efficiently. In some embodiments, the training of the weights uses a ring-based message passing architecture. In some embodiments, performance using a nested loop approach or nested loop fashion is provided. In inner iterations of the nested loop, PUs are scheduled and jobs are launched or re-started. In outer iterations of the nested loop, jobs are stopped, parameters are updated and the inner iteration is re-entered.

Abstract: A method, computer program, and computer system is provided for multimodal content retrieval. A search query corresponding to a request for content is received. Content features corresponding to a subset of content items from among a plurality of content items are retrieved based on receiving the search query. Similarity values are calculated between the search query and the retrieved content features. Attention scores are determined for the calculated similarity values. A content item is selected from among the subset of content items of the plurality of content items. The selected content item contains a content feature corresponding to a highest attention score of the attention scores.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: An apparatus for scrubbing an image may include a memory storing instructions; and a processor configured to execute the instructions to: receive an input image; input a preset public attribute to an encoder neural network; obtain a scrubbed feature from the input image based on the preset public attribute, via the encoder neural network; wherein the encoder neural network is trained based on an amount of information in the scrubbed feature about the input image, and an estimated public attribute estimated from the scrubbed feature.

Abstract: A method, computer program, and computer system is provided for multimodal content retrieval. A search query corresponding to a request for content is received. Content features corresponding to a subset of content items from among a plurality of content items are retrieved based on receiving the search query. Similarity values are calculated between the search query and the retrieved content features. Attention scores are determined for the calculated similarity values. A content item is selected from among the subset of content items of the plurality of content items. The selected content item contains a content feature corresponding to a highest attention score of the attention scores.

Abstract: An apparatus for scrubbing an image may include a memory storing instructions; and a processor configured to execute the instructions to: receive an input image; input a preset public attribute to an encoder neural network; obtain a scrubbed feature from the input image based on the preset public attribute, via the encoder neural network; wherein the encoder neural network is trained based on an amount of information in the scrubbed feature about the input image, and an estimated public attribute estimated from the scrubbed feature.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: A scheduling algorithm for scheduling training of deep neural network (DNN) weights on processing units identifies a next job to provisionally assign a processing unit (PU) based on a doubling heuristic. The doubling heuristic makes use of an estimated number of training sets needed to complete training of weights for a given job and/or a training speed function which indicates how fast the weights are converging. The scheduling algorithm solves a problem of efficiently assigning PUs when multiple DNN weight data structures must be trained efficiently. In some embodiments, the training of the weights uses a ring-based message passing architecture. In some embodiments, performance using a nested loop approach or nested loop fashion is provided. In inner iterations of the nested loop, PUs are scheduled and jobs are launched or re-started. In outer iterations of the nested loop, jobs are stopped, parameters are updated and the inner iteration is re-entered.