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: A light-emitting device includes a light-emitting assembly and a light-transmissive component. The light-emitting assembly includes a first bracket, a light-emitting element, and a first photosensitive element. The first bracket has a first surface and a second surface opposite to each other. Multiple first electrodes and multiple second electrodes are disposed at intervals on the first surface, and the light-emitting element and the first photosensitive element are disposed at intervals on the second surface. The light-emitting element is electrically connected to at least one of the multiple first electrodes. The first photosensitive element is electrically connected to at least one of the multiple second electrodes.

Abstract: Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement dynamic triplet convolution for convolutional neural networks are disclosed. An example apparatus disclosed herein for a convolutional neural network is to calculate one or more scalar kernels based on an input feature map applied to a layer of the convolutional neural network, ones of the one or more scalar kernels corresponding to respective dimensions of a static multidimensional convolutional filter associated with the layer of the convolutional neural network. The disclosed example apparatus is also to scale elements of the static multidimensional convolutional filter along a first one of the dimensions based on a first one of the one or more scalar kernels corresponding to the first one of the dimensions to determine a dynamic multidimensional convolutional filter associated with the layer of the convolutional neural network.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for teacher-free self-feature distillation training of machine-learning (ML) models. An example apparatus includes at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to perform a first comparison of (i) a first group of a first set of feature channels (FCs) of an ML model and (ii) a second group of the first set, perform a second comparison of (iii) a first group of a second set of FCs of the ML model and one of (iv) a third group of the first set or a first group of a third set of FCs of the ML model, adjust parameter(s) of the ML model based on the first and/or second comparisons, and, in response to an error value satisfying a threshold, deploy the ML model to execute a workload based on the parameter(s).

Abstract: A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method of embodiments, as described herein, 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: The present invention relates to the field of solid-phase extraction, and particularly to a solid-phase extraction material, and a preparation method and use thereof. The preparation method includes prepolymerizing the monomers N-vinylpyrrolidone and divinylbenzene in the presence of a chain transfer agent, adding prepolymer dropwise to an emulsion of monodispersed seed microspheres, swelling, and reacting to prepare white spheres; and functionalizing the white spheres, to obtain the solid-phase extraction material. The solid-phase extraction material prepared by the reaction has good spherical morphology, large specific surface area, and high ion exchange capacity. The prepared solid-phase extraction material functions in the separation and enrichment of PPCPs by means of a variety of forces with a high extraction rate. The extraction rate is basically maintained between 85% and 105%, and acidic, alkaline, neutral and amphoteric substances is capable of being selectively separated.

Abstract: The disclosure relates to decimal-bit network quantization of CNN models.

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: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps.

Abstract: The application discloses a system and method for centrifugal intrusion of molten metal into porous media and then solidification positioning, including: test cups, used for placing test medium and molten metal intrusion; a rotor block, used for mounting the test cups, where one end of each test cup for placing the test medium is far away from the rotor block; a constant temperature oil bath preheating device, used for preheating the test cups and the rotor block; a centrifugal device, internally provided with the rotor block, used for performing a centrifugal operation on the test cups, where the test cups and the rotor block are installed inside the centrifugal device after being preheated; and an infrared heating and compression refrigerating device, arranged inside the centrifugal device, used for controlling a temperature of the test cups.

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: 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: 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: 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.