https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Cognitive radio is viewed as a novel approach for improving the utilization of a precious natural resource: the radio electromagnetic spectrum. The cognitive radio, built on a software-defined radio, is defined as an intelligent wireless communication system that is aware of its environment and uses the methodology of understanding-by-building to learn from the environment and adapt to statistical variations in the input stimuli, with two primary objectives in mind: /spl middot/ highly reliable communication whenever and wherever needed; /spl middot/ efficient utilization of the radio spectrum. Following the discussion of interference temperature as a new metric for the quantification and management of interference, the paper addresses three fundamental cognitive tasks. 1) Radio-scene analysis. 2) Channel-state estimation and predictive modeling. 3) Transmit-power control and dynamic spectrum management. This work also discusses the emergent behavior of cognitive radio.

/pdf/cognitive-radio-brain-empowered-wireless-communications-9m6gu0vz1z.pdf

Cognitive radio: brain-empowered wireless communications

Monte Carlo methods are revolutionizing the on-line analysis of data in fields as diverse as financial modeling, target tracking and computer vision. These methods, appearing under the names of bootstrap filters, condensation, optimal Monte Carlo filters, particle filters and survival of the fittest, have made it possible to solve numerically many complex, non-standard problems that were previously intractable. This book presents the first comprehensive treatment of these techniques, including convergence results and applications to tracking, guidance, automated target recognition, aircraft navigation, robot navigation, econometrics, financial modeling, neural networks, optimal control, optimal filtering, communications, reinforcement learning, signal enhancement, model averaging and selection, computer vision, semiconductor design, population biology, dynamic Bayesian networks, and time series analysis. This will be of great value to students, researchers and practitioners, who have some basic knowledge of probability. Arnaud Doucet received the Ph. D. degree from the University of Paris-XI Orsay in 1997. From 1998 to 2000, he conducted research at the Signal Processing Group of Cambridge University, UK. He is currently an assistant professor at the Department of Electrical Engineering of Melbourne University, Australia. His research interests include Bayesian statistics, dynamic models and Monte Carlo methods. Nando de Freitas obtained a Ph.D. degree in information engineering from Cambridge University in 1999. He is presently a research associate with the artificial intelligence group of the University of California at Berkeley. His main research interests are in Bayesian statistics and the application of on-line and batch Monte Carlo methods to machine learning. Neil Gordon obtained a Ph.D. in Statistics from Imperial College, University of London in 1993. He is with the Pattern and Information Processing group at the Defence Evaluation and Research Agency in the United Kingdom. His research interests are in time series, statistical data analysis, and pattern recognition with a particular emphasis on target tracking and missile guidance.

/pdf/sequential-monte-carlo-methods-in-practice-3kfxeebn8e.pdf

Sequential Monte Carlo methods in practice

Planning algorithms are impacting technical disciplines and industries around the world, including robotics, computer-aided design, manufacturing, computer graphics, aerospace applications, drug design, and protein folding. This coherent and comprehensive book unifies material from several sources, including robotics, control theory, artificial intelligence, and algorithms. The treatment is centered on robot motion planning but integrates material on planning in discrete spaces. A major part of the book is devoted to planning under uncertainty, including decision theory, Markov decision processes, and information spaces, which are the “configuration spaces” of all sensor-based planning problems. The last part of the book delves into planning under differential constraints that arise when automating the motions of virtually any mechanical system. Developed from courses taught by the author, the book is intended for students, engineers, and researchers in robotics, artificial intelligence, and control theory as well as computer graphics, algorithms, and computational biology.

Planning Algorithms: Introductory Material

We introduce a novel fast algorithm for independent component analysis, which can be used for blind source separation and feature extraction. We show how a neural network learning rule can be transformed into a fixedpoint iteration, which provides an algorithm that is very simple, does not depend on any user-defined parameters, and is fast to converge to the most accurate solution allowed by the data. The algorithm finds, one at a time, all nongaussian independent components, regardless of their probability distributions. The computations can be performed in either batch mode or a semiadaptive manner. The convergence of the algorithm is rigorously proved, and the convergence speed is shown to be cubic. Some comparisons to gradient-based algorithms are made, showing that the new algorithm is usually 10 to 100 times faster, sometimes giving the solution in just a few iterations.

A fast fixed-point algorithm for independent component analysis

The theory and the applications of artificial neural networks, especially in a control field, are described. Recurrent networks and feedforward networks are discussed. Application to pattern recognition, information processing, design, planning, diagnosis, and control are examined. Hybrid systems using the neural networks, fuzzy sets, and artificial intelligence (AI) technologies are surveyed. >

Theory and applications of neural networks for industrial control systems

This paper presents a new prototype model of an underwater fish-like microrobot utilizing ionic conducting polymer film (ICPF) actuator as the servo actuator to realize swimming motion with three degrees of freedom. A biomimetic fish-like microrobot using ICPF actuator as a propulsion tail fin and a buoyancy adjuster for the swimming structure in water or aqueous medium is developed. The overall size of the underwater prototype fish shaped microrobot is 45 mm in length, 10 mm in width, and 4 mm in thickness. It has two tails with a fin driven respectively, a body posture adjuster, and a buoyancy adjuster. The moving characteristic of the underwater microrobot is measured by changing the frequency of input voltage from 0.1-5 Hz in water and the amplitude of input voltage from 0.5-10 V. The experimental results indicate that changing the amplitude and frequency of input voltage can control the swimming speed of proposed underwater microrobot.

A new type of fish-like underwater microrobot

Developing untethered millirobots that can adapt to harsh environments with high locomotion efficiency is of interest for emerging applications in various industrial and biomedical settings. Despite recent success in exploiting soft materials to impart sophisticated functions which are not available in conventional rigid robotics, it remains challenging to achieve superior performances in both wet and dry conditions. Inspired by the flexible, soft, and elastic leg/foot structures of many living organisms, here we report an untethered soft millirobot decorated with multiple tapered soft feet architecture. Such robot design yields superior adaptivity to various harsh environments with ultrafast locomotion speed (>40 limb length/s), ultra-strong carrying capacity (>100 own weight), and excellent obstacle-crossing ability (stand up 90° and across obstacle >10 body height). Our work represents an important advance in the emerging area of bio-inspired robotics and will find a wide spectrum of applications.

/pdf/a-bioinspired-multilegged-soft-millirobot-that-functions-in-2j1mgezcb4.pdf

A bioinspired multilegged soft millirobot that functions in both dry and wet conditions

Properties and potential applications of carbon nanotubes are summarized by emphasizing the aspects of nanoelectronics and nanoelectromechanical systems (NEMS). The main technologies for the assembly of nanodevices through nanomanipulations with scanning probe microscopes and nanorobotic manipulators are overviewed, focusing on that of nanotubes. Key techniques for nanoassembly include the preparation of nano building blocks and property characterization of them, the positioning of the building blocks with nanometer-scale resolution, and the connection of them. Nanorobotic manipulations, which are characterized by multiple degrees of freedom (DOFs) with both position and orientation control, independently actuated multiprobes, and a real-time observation system, are one of the most promising technologies for assembling complex nanodevices in three-dimensional space. With a nano laboratory, a prototype nanomanufacturing system based on a 16-DOF nanorobotic manipulation system, the assembly of nanodevices with multiwalled carbon nanotubes are presented. Nanotube-based building blocks are prepared by directly picking up, in situ property characterization, destructive fabrication, and shape modifications. Kinds of nanotube junctions, the fundamental elements for both nanoelectronics and NEMS, are constructed by positioning the building blocks together under the real-time observation with a field-emission scanning electron microscope, connecting them with naturally existing van der Waals forces, electron-beam-induced deposition, or mechanochemical bonding.

Assembly of nanodevices with carbon nanotubes through nanorobotic manipulations

The concept of the DRRS (dynamically reconfigurable robotic system) based on a cell structure is proposed for the next generation of robotic systems. The system can reorganize its configuration and its software to a given task, so that its level of flexibility and adaptability is much higher than that of the conventional robots. It consists of a lot of intelligent cells that have a fundamental mechanical function. Each cell can detach itself and recombine autonomously, depending on a task, e.g. To provide manipulators or mobile robots. The system can also be self-repairing and fault-tolerant. A decision method for cell-structured-manipulator configurations is proposed. >

Toshio Fukuda

Papers

Theory and applications of neural networks for industrial control systems

A new type of fish-like underwater microrobot

A bioinspired multilegged soft millirobot that functions in both dry and wet conditions

Assembly of nanodevices with carbon nanotubes through nanorobotic manipulations

Dynamically reconfigurable robotic system