Related Experiment Video
Updated: Aug 9, 2025
11:23
Lensless Fluorescent Microscopy on a Chip
Published on: August 17, 2011
17.7K
Lossy P-LDPC Codes for Compressing General Sources Using Neural Networks
Jinkai Ren1, Dan Song1, Huihui Wu2
1Department of Information and Communication Engineering, Xiamen University, Xiamen 361005, China.
Entropy (Basel, Switzerland)
|February 25, 2023
Summary
This study introduces an efficient lossy compression scheme using neural networks and low-density parity-check codes for Gaussian and Laplacian sources, achieving good distortion-rate performance.
Area of Science:
- Information Theory
- Signal Processing
- Machine Learning
Background:
- Designing efficient lossy compression for complex data sources remains a significant challenge.
- Approaching the theoretical distortion-rate limit is difficult with traditional block-based compression methods.
Purpose of the Study:
- To propose a novel lossy compression scheme for Gaussian and Laplacian sources.
- To improve upon conventional "quantization-compression" by introducing a "transformation-quantization" approach.
Main Methods:
- Utilizing neural networks for the transformation stage.
- Employing lossy protograph low-density parity-check codes for the quantization stage.
- Addressing neural network challenges like parameter updating and propagation optimization for system feasibility.
Main Results:
- The proposed scheme demonstrates effective distortion-rate performance.
- Simulation results validate the efficiency of the novel compression approach.
Conclusions:
- The "transformation-quantization" scheme offers a promising direction for efficient lossy compression.
- The integration of neural networks and advanced coding techniques enhances compression efficiency for specified sources.
Related Concept Videos
01:18Reducing Line Loss
184
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
184
01:25Neural Circuits
1.4K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.4K
01:22Lossy Lines and Overvoltages
116
Transmission-line series resistance and shunt conductance cause three primary effects: attenuation, distortion, and power losses.
Attenuation
When constant series resistance and shunt conductance are present, voltage and current equations are modified. The propagation constant indicates that voltage and current waves consist of both forward and backward traveling components. These waves attenuate as they propagate, with the attenuation factor related to the resistance and conductance. In a...
Attenuation
When constant series resistance and shunt conductance are present, voltage and current equations are modified. The propagation constant indicates that voltage and current waves consist of both forward and backward traveling components. These waves attenuate as they propagate, with the attenuation factor related to the resistance and conductance. In a...
116
01:20Downsampling
214
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
214
01:26Linear Approximation in Frequency Domain
121
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
121
01:22Upsampling
277
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
277