Filters








582 Hits in 2.7 sec

Artificial Neural Networks Jamming on the Beat [article]

Alexey Tikhonov, Ivan P. Yamshchikov
2021 arXiv   pre-print
Finally, the paper demonstrates that a simple artificial neural network could be trained to generate melodies corresponding with these drum patters used as inputs.  ...  Exploring a latent space of drum patterns one could generate new drum patterns with a given music style.  ...  Some of them are dedicated to drum patterns in particular, however there were several attempts to automate the process of music composition long before the era of artificial neural networks.  ... 
arXiv:2007.06284v2 fatcat:tjycsmob55at3phqwlkrrmtvjq

Two Applications of Deep Learning in the Physical Layer of Communication Systems [article]

Emil Björnson, Pontus Giselsson
2020 arXiv   pre-print
In particular, deep neural networks are capable of learning the complicated features in nature-made signals, such as photos and audio recordings, and use them for classification and decision making.  ...  By learning the key features and characteristics of the input signals, instead of requiring a human to first identify and model them, learned algorithms can beat many man-made algorithms.  ...  It is called an artificial neural network iff has a particular structure, such as the one illustrated in (b).  ... 
arXiv:2001.03350v1 fatcat:mckg66fvjbdxdnd7v4rq747pxe

Mobile Sentiment Analysis by Deep Learning Image Processing

Cristiana-Adriana Scaunasu, Paul Stefan Popescu, Marian Cristian Mihaescu
2020 International Joural of User-System Interaction  
Text or musical notes are generated by multiple trained neural network models and the user is the one that selects the best-generated result.  ...  Therefore, hybrid approaches where the user generates content by interacting with the artificial intelligence have provided better results.  ...  The approach used for the purpose of content generation is based on neural network language models.  ... 
doi:10.37789/ijusi.2020.13.3.1 fatcat:ipz2tr2krrbcxb56jjmrzytkya

Species differences in group size and electrosensory interference in weakly electric fishes: Implications for electrosensory processing

Sarah A. Stamper, Erika Carrera-G, Eric W. Tan, Vincent Fugère, Rüdiger Krahe, Eric S. Fortune
2010 Behavioural Brain Research  
In animals with active sensory systems, group size can have dramatic effects on the sensory information available to individuals.  ...  These results demonstrate categorical differences in social electrosensory-related activation of central nervous system circuits that may be related to the evolution of the jamming avoidance response that  ...  This work is dedicated to the memory of Helmuth Buchner.  ... 
doi:10.1016/j.bbr.2009.10.023 pmid:19874855 fatcat:rqksnhdacrhcbmkhitdf7fak6y

Expert Level control of Ramp Metering based on Multi-task Deep Reinforcement Learning [article]

Francois Belletti, Daniel Haziza, Gabriel Gomes, Alexandre M. Bayen
2017 arXiv   pre-print
We show how neural network based RL enables the control of discretized PDEs whose parameters are unknown, random, and time-varying.  ...  the opportunity to specialize its action policy so as to tailor it to the local parameters of the part of the system it is located in.  ...  Neural Networks The policy we train are implemented as Artificial Neural Networks, containing Artificial Neural wired together. 1) Artificial Neural Model: For p ∈ N, an Artificial Neural computes an output  ... 
arXiv:1701.08832v1 fatcat:5e55yvnemvceljh6cowc53oauy

Artificial Intelligence and Robotics [article]

Javier Andreu Perez, Fani Deligianni, Daniele Ravi, Guang-Zhong Yang
2018 arXiv   pre-print
The recent successes of AI have captured the wildest imagination of both the scientific communities and the general public.  ...  To understand the impact of AI, it is important to draw lessons from it's past successes and failures and this white paper provides a comprehensive explanation of the evolution of AI, its current status  ...  typical neural network.  ... 
arXiv:1803.10813v1 fatcat:p2czbmak4jcyxbtncqfqlkxtma

Landscape and training regimes in deep learning

Mario Geiger, Leonardo Petrini, Matthieu Wyart
2021 Physics reports  
We base our theoretical discussion on the (h, α) plane where h controls the number of parameters and α the scale of the output of the network at initialization, and provide new systematic measures of performance  ...  In this manuscript, we review recent results elucidating (i, ii) and the perspective they offer on the (still unexplained) curse of dimensionality paradox.  ...  Introduction One of the prerequisites of human or artificial intelligence is to make sense of data that often lie in large dimension.  ... 
doi:10.1016/j.physrep.2021.04.001 fatcat:5mb4nwhmpngi7euq3zxhjrsoqq

Identification and Control of PMSM Using Artificial Neural Network

Rajesh Kumar, R. A. Gupta, Ajay Kr. Bansal
2007 2007 IEEE International Symposium on Industrial Electronics  
There is almost no efficient tool available for writing MP3 audio tracks into sheets CHAPTER 3-ARTIFICIAL NEURAL NETWORK CLASSIFIER Introduction to Neural Networks Artificial neural network has been  ...  Artificial Neural Network is a pseudo network, constructed to replicate the human neural network in order to performs the tasks or functions of interest.  ... 
doi:10.1109/isie.2007.4374567 fatcat:hjhdj43wuzhpdlin5yi2sgmtb4

City-Wide Traffic Congestion Prediction based on CNN, LSTM and Transpose CNN

Navin Ranjan, Sovit Bhandari, Hong Ping Zhao, Hoon Kim, Pervez Khan
2020 IEEE Access  
network architecture formed by combing Convolutional Neural Network, Long Short-Term Memory, and Transpose Convolutional Neural Network to extract the spatial and temporal information from the input image  ...  Forecasting the congestion level of a road network timely can prevent its formation and increase the efficiency and capacity of the road network.  ...  neural network (ANN).  ... 
doi:10.1109/access.2020.2991462 fatcat:6cho7c4wsfdy5fpfxg4avvvpoi

Encoding and processing biologically relevant temporal information in electrosensory systems

E. S. Fortune, G. J. Rose, M. Kawasaki
2006 Journal of Comparative Physiology A. Sensory, neural, and behavioral physiology  
Certain species exhibit a behavior that relies almost exclusively on temporal information for its control: the jamming avoidance response or "JAR."  ...  These distantly related groups use similar strategies for neural computations of information on the order of microseconds, milliseconds, and seconds.  ...  Certain species exhibit a behavior that relies almost exclusively on temporal information for its control: the jamming avoidance response or ''JAR.''  ... 
doi:10.1007/s00359-006-0102-0 pmid:16450118 fatcat:4vnu7l6ps5fxnl3yzlgddgrike

The anomalous tango of hemocyte migration in Drosophila melanogaster embryos [article]

Nickolay Korabel, Giuliana D. Clemente, Daniel Han, Felix Feldman, Tom H. Millard, Thomas Andrew Waigh
2021 arXiv   pre-print
Every hemocyte cell in one half of an embryo was tracked during embryogenesis and analysed using a deep learning neural network.  ...  The anomalous motility of the hemocytes oscillated in time with alternating epoques of varying persistent motion.  ...  Data availability The data that support the findings of this study are available from the corresponding author upon reasonable request.  ... 
arXiv:2109.03797v1 fatcat:kyb3w6jyvrhpnonlshpugfjuxq

Wireless Communication, Sensing, and REM: A Security Perspective

Haji M. Furqan, Muhammad Sohaib J. Solaija, Halise Turkmen, Huseyin Arslan
2021 IEEE Open Journal of the Communications Society  
network [16] .  ...  Corresponding to the aforementioned intentions of the malicious attackers, the network strives to guarantee that its nodes and users are protected.  ...  Over the last few years, industrial giants like Microsoft and IBM have put significant efforts towards it, with the former having demonstrated the possibility of applying neural networks on encrypted data  ... 
doi:10.1109/ojcoms.2021.3054066 fatcat:klhorbflvvdrlkqyndctn3lwtq

SINKHOLE ATTACK DETECTION IN MANET USING SWARM INTELLIGENCE TECHNIQUES

Laxmi ., Dr. Rashmi Popli
2020 International Journal of Engineering Applied Sciences and Technology  
The information is attracted by sinkhole node from the neighboring node and after that, it counterfeits the steering data that makes the local area network know its way on specific node.  ...  Sinkhole attack may be a network layer attack, which affect the overall network.  ...  ABC (Artificial Bee Colony) is used with OLSR protocol [4] . In this research, ABC algorithm is used for optimization and the ANN (Artificial Neural Network) is used for classification.  ... 
doi:10.33564/ijeast.2020.v05i04.021 fatcat:pgowo4olnbb4hn75msuvwfspde

Nonlinear Trend Analysis of Mill Fan System Vibrations for Predictive Maintenance and Diagnostics

Mincho B. Hadjiski, Lyubka A. Doukovska, Stefan L. Kojnov
2012 International Journal of Electronics and Telecommunications  
The subject is a device from Maritsa East 2 thermal power plant a mill fan. The choice of the given power plant is not occasional. This is the largest thermal power plant on the Balkan Peninsula.  ...  This paper addresses the needs of the Maritsa East 2 Complex aiming to improve the ecological parameters of the electro energy production process.  ...  Between the artificial intelligence techniques have become particularly popular the methods of artificial neural networks and neurofuzzy networks.  ... 
doi:10.2478/v10177-012-0048-9 fatcat:w6kfarjfcjfflkmggunpadlytm

Adversarial Machine Learning in Wireless Communications using RF Data: A Review [article]

Damilola Adesina, Chung-Chu Hsieh, Yalin E. Sagduyu, Lijun Qian
2021 arXiv   pre-print
First, the background of AML attacks on deep neural networks is discussed and a taxonomy of AML attack types is provided.  ...  This paper presents a comprehensive review of the latest research efforts focused on AML in wireless communications while accounting for the unique characteristics of wireless systems.  ...  DL Models Papers Feedforward Neural Network [29], [57]-[62] Convolutional Neural Network [28], [30]-[33], [35], [38]-[41], [60], [63]-[73] Recurrent Neural Network [74] Reinforcement Learning  ... 
arXiv:2012.14392v2 fatcat:4d3x2scwjvh33drc745mmc4gvy
« Previous Showing results 1 — 15 out of 582 results