AIMC Topic: Data Compression

Clear Filters Showing 71 to 80 of 147 articles

Decision tree accelerated CTU partition algorithm for intra prediction in versatile video coding.

PloS one
Versatile video coding (VVC) achieves enormous improvement over the advanced high efficiency video coding (HEVC) standard due to the adoption of the quadtree with nested multi-type tree (QTMT) partition structure and other coding tools. However, the ...

BP Neural Network Based on Simulated Annealing Algorithm Optimization for Financial Crisis Dynamic Early Warning Model.

Computational intelligence and neuroscience
Financial early warning mechanism is of great significance to the long-term healthy development and stable operation of listed enterprises. This paper adopts the logistic regression early warning model and BP neural network early warning model. Based...

Weak sub-network pruning for strong and efficient neural networks.

Neural networks : the official journal of the International Neural Network Society
Pruning methods to compress and accelerate deep convolutional neural networks (CNNs) have recently attracted growing attention, with the view of deploying pruned networks on resource-constrained hardware devices. However, most existing methods focus ...

Nonlinear tensor train format for deep neural network compression.

Neural networks : the official journal of the International Neural Network Society
Deep neural network (DNN) compression has become a hot topic in the research of deep learning since the scale of modern DNNs turns into too huge to implement on practical resource constrained platforms such as embedded devices. Among variant compress...

No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks.

Sensors (Basel, Switzerland)
A common technique for compressing a neural network is to compute the -rank ℓ2 approximation Ak of the matrix A∈Rn×d via SVD that corresponds to a fully connected layer (or embedding layer). Here, is the number of input neurons in the layer, is the...

MedQ: Lossless ultra-low-bit neural network quantization for medical image segmentation.

Medical image analysis
Implementing deep convolutional neural networks (CNNs) with boolean arithmetic is ideal for eliminating the notoriously high computational expense of deep learning models. However, although lossless model compression via weight-only quantization has ...

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference.

Sensors (Basel, Switzerland)
Edge-cloud collaborative inference can significantly reduce the delay of a deep neural network (DNN) by dividing the network between mobile edge and cloud. However, the in-layer data size of DNN is usually larger than the original data, so the commun...

Quality Enhancement of Compressed Vibrotactile Signals Using Recurrent Neural Networks and Residual Learning.

IEEE transactions on haptics
We present a neural network-based compression artifact removal technique for vibrotactile signals. The proposed decoder-side quality enhancement approach is based on recurrent neural networks (RNNs) and the principle of residual learning. We use a to...

Periodicity and multi-periodicity generated by impulses control in delayed Cohen-Grossberg-type neural networks with discontinuous activations.

Neural networks : the official journal of the International Neural Network Society
This paper discusses the periodicity and multi-periodicity in delayed Cohen-Grossberg-type neural networks (CGNNs) possessing impulsive effects, whose activation functions possess discontinuities and are allowed to be unbounded or nonmonotonic. Based...

Classification of Cattle Behaviours Using Neck-Mounted Accelerometer-Equipped Collars and Convolutional Neural Networks.

Sensors (Basel, Switzerland)
Monitoring cattle behaviour is core to the early detection of health and welfare issues and to optimise the fertility of large herds. Accelerometer-based sensor systems that provide activity profiles are now used extensively on commercial farms and h...