In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

Certain aspects of the present disclosure provide techniques for performing machine learning computations in a compute in memory (CIM) array comprising a plurality of bit cells, including: determining that a sparsity of input data to a machine learning model exceeds an input data sparsity threshold; disabling one or more bit cells in the CIM array based on the sparsity of the input data prior to processing the input data; processing the input data with bit cells not disabled in the CIM array to generate an output value; applying a compensation to the output value based on the sparsity to generate a compensated output value; and outputting the compensated output value.

Techniques for implementing a performance-adaptive sampling strategy towards fast and accurate graph neural networks are provided. In one technique, a graph that comprises multiple nodes and edges connecting the nodes is stored. An embedding for each node is initialized, as well as a sampling policy for sampling neighbors of nodes. One or more machine learning techniques are used to train a graph neural network and learn embeddings for the nodes. Using the one or more machine learning techniques comprises, for each node: (1) selecting, based on the sampling policy, a set of neighbors of the node; (2) based on the graph neural network and embeddings for the node and the set of neighbors, computing a performance loss; and (3) based on a gradient of the performance loss, modifying the sampling policy.

A system and method are disclosed for secure multi-party computations. The system performs operations including establishing an API for coordinating joint operations between a first access point and a second access point related to performing a secure prediction task in which the first access point and the second access point will perform private computation of first data and second data without the parties having access to each other's data. The operations include storing a list of assets representing metadata about the first data and the second data, receiving a selection of the second data for use with the first data, managing an authentication and authorization of communications between the first access point and the second access point and performing the secure prediction task using the second data operating on the first data.

Disclosed herein are an apparatus and method for classifying clothing attributes based on deep learning. The apparatus includes memory for storing at least one program and a processor for executing the program, wherein the program includes a first classification unit for outputting a first classification result for one or more attributes of clothing worn by a person included in an input image, a mask generation unit for outputting a mask tensor in which multiple mask layers respectively corresponding to principal part regions obtained by segmenting a body of the person included in the input image are stacked, a second classification unit for outputting a second classification result for the one or more attributes of the clothing by applying the mask tensor, and a final classification unit for determining and outputting a final classification result for the input image based on the first classification result and the second classification result.

A system and method are provided for providing advisory notifications to mobile applications. The method includes interfacing the server device with at least one endpoint within an enterprise system and storing a model trained by a machine learning engine to automatically determine advisory notifications relevant to client data sets stored by the endpoint(s) and/or the at least one endpoint. The method also includes determining a current state of a client account, using the model to determine an advisory notification for the client account based on the current state, referring to a set of rules to determine when to provide the advisory notification in the mobile application, and in what portion of the mobile application to display the notification; and sending the advisory notification via the communications module to a client device to display the advisory notification in the mobile application.

A method of generating a pre-training model, an electronic device and a storage medium, which relate to a field of an artificial intelligence technology, in particular to a computer vision and deep learning technology. The method includes: determining a performance index set corresponding to a candidate model structure set, the candidate model structure set is determined from a plurality of model structures included in a search space, and the search space is a super-network-based search space; determining, from the candidate model structure set, a target model structure corresponding to each chip according to the performance index set, each target model structure is a model structure meeting a performance index condition; and determining, for each chip, the target model structure corresponding to the chip as a pre-training model corresponding to the chip, the chip is configured to run the pre-training model corresponding to the chip.

A human-object interaction detection method, a neural network and a training method therefor is provided. The human-object interaction detection method includes: extracting a plurality of first target features and one or more first motion features from an image feature of an image to be detected; fusing each first target feature and some of the first motion features to obtain enhanced first target features; fusing each first motion feature and some of the first target features to obtain enhanced first motion features; processing the enhanced first target features to obtain target information of a plurality of targets including human targets and object targets; processing the enhanced first motion features to obtain motion information of one or more motions, where each motion is associated with one human target and one object target; and matching the plurality of targets with the one or more motions to obtain a human-object interaction detection result.

The present invention is a molecular graph representation learning method based on contrastive learning, the method comprising: obtaining a molecular fingerprint representation of each molecule, and calculating a similarity between each two molecular fingerprints; collecting a full amount of chemical functional group information, and matching a corresponding functional group for each atom in the molecule; using a heterogeneous graph to model a molecular graph; using a RGCN in the structure-aware molecular encoder to encode the representation of each atom in the molecule and the representation of the functional group to which the atom belongs, and mapping the molecule to a feature space through an aggregation function to obtain a structure-aware feature representation; according to the fingerprint similarity between molecules, selecting positive and negative samples, and carrying out a comparative learning in the feature space; obtaining the structure-aware molecular encoder by using the contrastive learning method for training on a large-sample molecular dataset, and applying the structure-aware molecular encoder to a prediction task of downstream molecular attributes. The present invention helps to capture more abundant molecular structure information and solve the problem on molecular property prediction.

An audio encoding bit rate prediction model training method is performed by a computer device. The method includes: obtaining a sample audio feature parameter corresponding to each of sample audio frames in a first sample audio; performing encoding bit rate prediction on the sample audio feature parameter through an encoding bit rate prediction model, to obtain a sample encoding bit rate for each of the sample audio frames; performing audio encoding on the sample audio frames based on the corresponding sample encoding bit rates to generate sample audio data corresponding to the sample audio frames; performing audio decoding on the sample audio data, to obtain a second sample audio corresponding to the sample audio data; and training the encoding bit rate prediction model based on the first sample audio and the second sample audio until a sample encoding quality score reaches a target encoding quality score.