Binary sequences with good aperiodic autocorrelation functions obtained by neural network search

1997 ◽  
Vol 33 (8) ◽  
pp. 688 ◽  
Author(s):  
F. Hu ◽  
P.Z. Fan ◽  
M. Darnell ◽  
F. Jin
Keyword(s):  
Neural Network ◽  
Binary Sequences ◽  
Autocorrelation Functions ◽  
Network Search ◽  
Aperiodic Autocorrelation

scholarly journals Structure and Functions of a Replicative Neuro-like Module

2020 ◽  
Vol 19 (4) ◽  
pp. 803-828
Author(s):  
Ivan Stepanyan ◽  
Andrey Khomich
Keyword(s):  
Neural Network ◽  
Intelligent Systems ◽  
High Efficiency ◽  
Stochastic Dynamics ◽  
Binary Sequences ◽  
Chinese Room ◽  
Evolutionary Mechanisms ◽  
Neural Network System ◽  
Unified Algorithm ◽  
The Given

The given work describes a technology of construction of neural network system of artificial intellect (AI) at a junction of declarative programming and machine training on the basis of modelling of cortical columns. Evolutionary mechanisms, using available material and relatively simple phenomena, have created complex intelligent systems. From this, the authors conclude that AI should also be based on simple but scalable and biofeasible algorithms, in which the stochastic dynamics of cortical neural modules allow to find solutions to of complex problems quickly and efficiently.. Purpose: Algorithmic formalization at the level of replicative neural network complexes - neocortex columns of the brain. Methods: The basic AI module is presented as a specialization and formalization of the concept "Chinese room" introduced by John Earle. The results of experiments on forecasting binary sequences are presented. The computer simulation experiments have shown high efficiency in implementing the proposed algorithms. At the same time, instead of using for each task a carefully selected and adapted separate method with partially equivalent restatement of tasks, the standard unified approach and unified algorithm parameters were used. It is concluded that the results of the experiments show the possibility of effective applied solutions based on the proposed technology. Practical value: the presented technology allows creating self-learning and planning systems.

Research and Analysis of Autocorrelation Functions of Code Sequences Formed on the Basis of Monocyclic Quasi-Orthogonal Matrices

2018 ◽  
pp. 9-14 ◽  
Author(s):  
V. A. Nenashev ◽  
A. M. Sergeev ◽  
E. A. Kapranova
Keyword(s):  
Data Transmission ◽  
Noise Immunity ◽  
Binary Sequences ◽  
Digital Data ◽  
Electromagnetic Environment ◽  
Autocorrelation Functions ◽  
Radar Systems ◽  
Radio Signals ◽  
Barker Codes ◽  
Compression Characteristics

Introduction: Barker codes representing binary sequences (codes) of finite lengths 2, 3, 4, 5, 7, 11 and 13 are widely used in solving the problem of increasing the noise immunity of radar channels. However, the code sequences for n > 13 are unknown. Sequences derived from quasi-orthogonal Mersenne matrices also have not been used for these purposes.Purpose: Studying the ways to compress a complex modulated signal by Mersenne sequences obtained from the first rows of a monocyclic quasi-orthogonal Mersenne matrix, as an alternative to Barker codes.Results:It has been found out that the characteristics of autocorrelation functions for Mersenne codes 3, 7 and 11 exceed those for Barker codes. This is a basis for ensuring greater noise immunity of probing signals in radar channels, as well as for increasing the probability of their correct detection, proving the expediency of their application for amplitude and phase modulation of radio signals.Practical relevance:The obtained results allow you to increase the compression characteristics in radar systems when solving the problem of detecting targets under noise and interference. The wide application of Barker codes of length 3, 7 and 11 in digital data transmission systems provides a special interest in similar Mersenne codes when implementing noise-resistant data transmission in radio channels in a complex electromagnetic environment. Discussion: An unresolved problem is the non-symmetry of elements in a coding Mersenne sequence. This problem can be solved either by special synthesis of a phase-modulated signal or by finding new approaches to their compression.

SwingNet

2021 ◽  
Vol 5 (3) ◽  
pp. 1-21
Author(s):  
Hong Jia ◽  
Jiawei Hu ◽  
Wen Hu
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Depth Sensor ◽  
Sports Analytics ◽  
Adversarial Learning ◽  
Depth Sensors ◽  
Network Search ◽  
In The Wild ◽  
Motion Measurements ◽  
Independent Model

Sports analytics in the wild (i.e., ubiquitously) is a thriving industry. Swing tracking is a key feature in sports analytics. Therefore, a centimeter-level tracking resolution solution is required. Recent research has explored deep neural networks for sensor fusion to produce consistent swing-tracking performance. This is achieved by combining the advantages of two sensor modalities (IMUs and depth sensors) for golf swing tracking. Here, the IMUs are not affected by occlusion and can support high sampling rates. Meanwhile, depth sensors produce significantly more accurate motion measurements than those produced by IMUs. Nevertheless, this method can be further improved in terms of accuracy and lacking information for different domains (e.g., subjects, sports, and devices). Unfortunately, designing a deep neural network with good performance is time consuming and labor intensive, which is challenging when a network model is deployed to be used in new settings. To this end, we propose a network based on Neural Architecture Search (NAS), called SwingNet, which is a regression-based automatic generated deep neural network via stochastic neural network search. The proposed network aims to learn the swing tracking feature for better prediction automatically. Furthermore, SwingNet features a domain discriminator by using unsupervised learning and adversarial learning to ensure that it can be adaptive to unobserved domains. We implemented SwingNet prototypes with a smart wristband (IMU) and smartphone (depth sensor), which are ubiquitously available. They enable accurate sports analytics (e.g., coaching, tracking, analysis and assessment) in the wild. Our comprehensive experiment shows that SwingNet achieves less than 10 cm errors of swing tracking with a subject-independent model covering multiple sports (e.g., golf and tennis) and depth sensor hardware, which outperforms state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document