Opening the Black Box of Deep Neural Networks in Physical Layer
Communication
- URL: http://arxiv.org/abs/2106.01124v1
- Date: Wed, 2 Jun 2021 12:48:15 GMT
- Title: Opening the Black Box of Deep Neural Networks in Physical Layer
Communication
- Authors: Jun Liu, Kai Mei, Dongtang Ma and Jibo Wei
- Abstract summary: Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems.
In this letter, we aim to quantitatively analyse why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques and its cost in terms of computational complexity.
- Score: 5.4430666212714005
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep Neural Network (DNN)-based physical layer techniques are attracting
considerable interest due to their potential to enhance communication systems.
However, most studies in the physical layer have tended to focus on the
implement of DNN but not to theoretically understand how does a DNN work in a
communication system. In this letter, we aim to quantitatively analyse why DNNs
can achieve comparable performance in the physical layer comparing with
traditional techniques and its cost in terms of computational complexity. We
further investigate and also experimentally validate how information is flown
in a DNN-based communication system under the information theoretic concepts.
Related papers
- Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods [33.377770671553336]
Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs)
In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance.
arXiv Detail & Related papers (2024-05-06T09:58:54Z) - Deep Neural Networks via Complex Network Theory: a Perspective [3.1023851130450684]
Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging statistical physics with graph theory, provides a method for interpreting neural networks by analysing their weights and neuron structures.
In this work, we extend the existing CNT metrics with measures that sample from the DNNs' training distribution, shifting from a purely topological analysis to one that connects with the interpretability of deep learning.
arXiv Detail & Related papers (2024-04-17T08:42:42Z) - Transferability of coVariance Neural Networks and Application to
Interpretable Brain Age Prediction using Anatomical Features [119.45320143101381]
Graph convolutional networks (GCN) leverage topology-driven graph convolutional operations to combine information across the graph for inference tasks.
We have studied GCNs with covariance matrices as graphs in the form of coVariance neural networks (VNNs)
VNNs inherit the scale-free data processing architecture from GCNs and here, we show that VNNs exhibit transferability of performance over datasets whose covariance matrices converge to a limit object.
arXiv Detail & Related papers (2023-05-02T22:15:54Z) - Spiking Neural Network Decision Feedback Equalization [70.3497683558609]
We propose an SNN-based equalizer with a feedback structure akin to the decision feedback equalizer (DFE)
We show that our approach clearly outperforms conventional linear equalizers for three different exemplary channels.
The proposed SNN with a decision feedback structure enables the path to competitive energy-efficient transceivers.
arXiv Detail & Related papers (2022-11-09T09:19:15Z) - Deep Neural Networks as Complex Networks [1.704936863091649]
We use Complex Network Theory to represent Deep Neural Networks (DNNs) as directed weighted graphs.
We introduce metrics to study DNNs as dynamical systems, with a granularity that spans from weights to layers, including neurons.
We show that our metrics discriminate low vs. high performing networks.
arXiv Detail & Related papers (2022-09-12T16:26:04Z) - Deep Reinforcement Learning Guided Graph Neural Networks for Brain
Network Analysis [61.53545734991802]
We propose a novel brain network representation framework, namely BN-GNN, which searches for the optimal GNN architecture for each brain network.
Our proposed BN-GNN improves the performance of traditional GNNs on different brain network analysis tasks.
arXiv Detail & Related papers (2022-03-18T07:05:27Z) - Theoretical Analysis of Deep Neural Networks in Physical Layer
Communication [8.015654492208368]
Deep neural network (DNN)-based physical layer communication techniques have attracted considerable interest.
In this paper, we quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques.
arXiv Detail & Related papers (2022-02-21T02:36:35Z) - Topological Measurement of Deep Neural Networks Using Persistent
Homology [0.7919213739992464]
The inner representation of deep neural networks (DNNs) is indecipherable.
Persistent homology (PH) was employed for investigating the complexities of trained DNNs.
arXiv Detail & Related papers (2021-06-06T03:06:15Z) - Progressive Tandem Learning for Pattern Recognition with Deep Spiking
Neural Networks [80.15411508088522]
Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency.
We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
arXiv Detail & Related papers (2020-07-02T15:38:44Z) - Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey [77.99182201815763]
Deep Neural Networks (DNNs) achieve state-of-the-art results in many different problem settings.
DNNs are often treated as black box systems, which complicates their evaluation and validation.
One promising field, inspired by the success of convolutional neural networks (CNNs) in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations.
arXiv Detail & Related papers (2020-06-30T14:56:05Z) - Architecture Disentanglement for Deep Neural Networks [174.16176919145377]
We introduce neural architecture disentanglement (NAD) to explain the inner workings of deep neural networks (DNNs)
NAD learns to disentangle a pre-trained DNN into sub-architectures according to independent tasks, forming information flows that describe the inference processes.
Results show that misclassified images have a high probability of being assigned to task sub-architectures similar to the correct ones.
arXiv Detail & Related papers (2020-03-30T08:34:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.