Abstract: A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.

Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

Abstract: This application provides a communication method integrated with trusted measurement and an apparatus. The method includes: A first network element sends a first request message, where the first request message is for requesting to verify whether terminal device is trusted. The first network element receives a first response message, where the first response message is for verifying whether the terminal device is trusted.

Abstract: A method includes: a network function service consumer sends a service request message, where the service request message is used to request to obtain a service provided by a network function service provider. The network function service consumer receives a service response message, where the service response message indicates whether the service request message is accepted, and further indicates a result of trustworthiness verification of the network function service consumer. The method helps the network function service provider verify, before providing the network service, an identity of the network function service consumer and determine whether the network function service consumer is trusted, to help improve security of communication between core network elements and improve security of a core network device.

Abstract: A training method based on an improved protograph neural decoder includes the following steps: a to-be-trained decoding network is constructed based on an initial variable sub-network layer, an initial check sub-network layer and a preset shuffled belief-propagation (BP) sub-network layer; the initial variable sub-network layer, the initial check sub-network layer and the preset shuffled BP sub-network layer are updated and trained by calculating log-likelihood ratio (LLR) based on a preset mean square error loss function and a preset decoder objective function to obtain a target protograph neural decoder; and the preset mean square error loss function is configured to calculate a loss value between output information of the check sub-network layer and the preset shuffled BP sub-network layer. The target protograph neural decoder includes an optimized variable sub-network layer, an optimized check sub-network layer and an optimized shuffled BP sub-network layer. A training device is also provided.

Abstract: Methods, apparatus, systems and articles of manufacture for loss-error-aware quantization of a low-bit neural network are disclosed. An example apparatus includes a network weight partitioner to partition unquantized network weights of a first network model into a first group to be quantized and a second group to be retrained. The example apparatus includes a loss calculator to process network weights to calculate a first loss. The example apparatus includes a weight quantizer to quantize the first group of network weights to generate low-bit second network weights. In the example apparatus, the loss calculator is to determine a difference between the first loss and a second loss. The example apparatus includes a weight updater to update the second group of network weights based on the difference. The example apparatus includes a network model deployer to deploy a low-bit network model including the low-bit second network weights.

Abstract: Methods and apparatus to perform parallel double-batched self-distillation in resource-constrained image recognition environments are disclosed herein. Example apparatus disclosed herein are to identify a source data batch and an augmented data batch, the augmented data generated based on at least one data augmentation technique. Disclosed example apparatus is also to share one or more parameters between a student neural network corresponding to the source data batch and a teacher neural network corresponding to the augmented data batch, the one or more parameters including one or more convolution layers to be shared between the teacher neural network and the student neural network. Disclosed example apparatus is further to align knowledge corresponding to the teacher neural network and the student neural network, the knowledge corresponding to the one or more parameters shared between the student neural network and the teacher neural network.

Abstract: This disclosure describes systems, methods, and devices related to real-time multi-person three-dimensional pose tracking using a single camera.

Abstract: An apparatus, method, device and medium for dynamic quadruple convolution in a 3-dimensional (3D) convolutional neural network (CNN) are provided. The method includes: a multi-dimensional attention block configured to: receive an input feature map of a video data sample; and dynamically generate convolutional kernel scalars along four dimensions of a 3-dimensional convolution kernel space based on the input feature map, the four dimensions comprising an output channel number, an input channel number, a temporal size and a spatial size; and a convolution block configured to sequentially multiply the generated convolutional kernel scalars with a static 3D convolution kernel in a matrix-vector product way to obtain a dynamic kernel of dynamic quadruple convolution.

Abstract: A planetary bevel gear automatic limited slip differential includes five portions that are a main differential, a planetary bevel gear controller, a left drive axle shaft, a right drive axle shaft, and clutches. The planetary bevel gear controller includes an outer control unit and an inner control unit, the outer control unit includes four planetary bevel gears on an outer layer and a bevel gear fixed on a housing, and the inner control unit includes inner planetary bevel gears on an inner side and two bevel gears which have the same parameters and are meshed with the planetary bevel gears. The bevel gears are fixedly connected with outer rings of two overrunning clutches, respectively, and inner rings of the overrunning clutches and the right drive axle shaft are connected together by splines.

Abstract: Techniques related to compressing a pre-trained dense deep neural network to a sparsely connected deep neural network for efficient implementation are discussed. Such techniques may include iteratively pruning and splicing available connections between adjacent layers of the deep neural network and updating weights corresponding to both currently disconnected and currently connected connections between the adjacent layers.

Abstract: The invention provides novel compositions and methods for improving the transformation of monocot seed excised embryo explants, which may include one or more steps of explant preparation, explant rehydration, Rhizobiales bacterium inoculation and co-culture, bud induction, extended bud induction, or regeneration of genetically modified plants or plant parts. The methods provided herein may include transforming at least one plant cell of the embryo explant with a heterologous polynucleotide by inoculating the embryo explant with a Rhizobiales bacterium comprising the heterologous polynucleotide. The methods provided herein also include methods of regenerating a genetically modified plant or plant part from a transformed or edited plant cell or explant.

Abstract: Technology to conduct image sequence/video analysis can include a processor, and a memory coupled to the processor, the memory storing a neural network, the neural network comprising a plurality of convolution layers, a network depth relay structure comprising a plurality of network depth calibration layers, where each network depth calibration layer is coupled to an output of a respective one of the plurality of convolution layers, and a feature dimension relay structure comprising a plurality of feature dimension calibration slices, where the feature dimension relay structure is coupled to an output of another layer of the plurality of convolution layers. Each network depth calibration layer is coupled to a preceding network depth calibration layer via first hidden state and cell state signals, and each feature dimension calibration slice is coupled to a preceding feature dimension calibration slice via second hidden state and cell state signals.

Abstract: Technology to conduct image sequence/video analysis can include a processor, and a memory coupled to the processor, the memory storing a neural network, the neural network comprising a plurality of convolution layers, and a plurality of normalization layers arranged as a relay structure, wherein each normalization layer is coupled to and following a respective one of the plurality of convolution layers. The plurality of normalization layers can be arranged as a relay structure where a normalization layer for a layer (k) is coupled to and following a normalization layer for a preceding layer (k?1). The normalization layer for the layer (k) is coupled to the normalization layer for the preceding layer (k?1) via a hidden state signal and a cell state signal, each signal generated by the normalization layer for the preceding layer (k?1). Each normalization layer (k) can include a meta-gating unit (MGU) structure.

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

Abstract: Techniques are disclosed for providing improved pose tracking of a subject using a 2D camera and generating a 3D image that recreates the pose of the subject. A 3D skeleton map is estimated from a 2D skeleton map of the subject using, for example, a neural network. A template 3D skeleton map is accessed or generated having bone segments that have lengths set using, for instance, anthropometry statistics based on a given height of the template 3D skeleton map. An improved 3D skeleton map is then produced by at least retargeting one or more of the plurality of bone segments of the estimated 3D skeleton map to more closely match the corresponding template bone segments of the template 3D skeleton map. The improved 3D skeleton map can then be animated in various ways (e.g., using various skins or graphics) to track corresponding movements of the subject.

Abstract: A loudspeaker and an electronic system are disclosed. The loudspeaker includes a base, a loudspeaker body and a first driver. The loudspeaker body is disposed on the base and defines an up and down direction of the loudspeaker, and the loudspeaker body is rotatable around the up and down direction with respect to the base. The first driver can drive the loudspeaker body to rotate with respect to the base.

Abstract: Techniques related to application of deep neural networks to video for video recognition and understanding are discussed. A feature map of a deep neural network for a current time stamp of input video is standardized to a standardized feature map and pooled to a feature vector. The feature vector and transform parameters for a prior time stamp are used to generate transform parameters for the current time stamp based on application of a meta temporal relay. The resultant current time stamp transform parameters, such as a hidden state and a cell state of the meta temporal relay, are used to transform the standardized feature map to a normalized feature map for use by a subsequent layer of the deep neural network.