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

Deep learning in neural networks

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

In his introduction to this detailed survey of knowledge of insect societies, the author points out that research on insect sociology has proceeded in three phases, the natural history phase, the physiological phase and the population-biology phase. Advances in the first two phases have permitted embarkation in the third phase on a more rigorous theory of social evolution based on population genetics and writing this book, the author wished to relate the three phases of research on insects and to express insect sociology as population biology. A glossary of terms, a considerable bibliography and a general index are included. Other CABI sites 

The Insect Societies

https://dialnet.unirioja.es/descarga/articulo/4511387.pdf

The origins of order. Self-organization and selection in evolution

NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data

Unlike the traditional robot calibration methods, which need external expensive calibration apparatus and elaborate setups to measure the 3D feature points in the reference frame, a vision-based self-calibration method for a serial robot manipulator, which only requires a ground-truth scale in the reference frame, is proposed in this paper. The proposed algorithm assumes that the camera is rigidly attached to the robot end-effector, which makes it possible to obtain the pose of the manipulator with the pose of the camera. By designing a manipulator movement trajectory, the camera poses can be estimated up to a scale factor at each configuration with the factorization method, where a nonlinear least-square algorithm is applied to improve its robustness. An efficient approach is proposed to estimate this scale factor. The great advantage of this self-calibration method is that only image sequences of a calibration object and a ground-truth length are needed, which makes the robot calibration procedure more autonomous in a dynamic manufacturing environment. Simulations and experimental studies on a PUMA 560 robot reveal the convenience and effectiveness of the proposed robot self-calibration approach.

Autonomous robot calibration using vision technology

Developmental robotics is also known as epigenetic robotics. We propose in this paper that there is one substantial difference between developmental robotics and epigenetic robotics, since epigenetic robotics concentrates primarily on modeling the development of cognitive elements of living systems in robotic systems, such as language, emotion, and social skills, while developmental robotics should also cover the modeling of neural and morphological development in single- and multirobot systems. With the recent rapid advances in evolutionary developmental biology and systems biology, increasing genetic and cellular principles underlying biological morphogenesis have been revealed. These principles are helpful not only in understanding biological development, but also in designing self-organizing, self-reconfigurable, and self-repairable engineered systems. In this paper, we propose morphogenetic robotics, an emerging new field in developmental robotics, is an important part of developmental robotics in addition to epigenetic robotics. By morphogenetic robotics, we mean a class of methodologies in robotics for designing self-organizing, self-reconfigurable, and self-repairable single- or multirobot systems, using genetic and cellular mechanisms governing biological morphogenesis. We categorize these methodologies into three areas, namely, morphogenetic swarm robotic systems, morphogenetic modular robots, and morphogenetic body and brain design for robots. Examples are provided for each of the three areas to illustrate the main ideas underlying the morphogenetic approaches to robotics.

Morphogenetic Robotics: An Emerging New Field in Developmental Robotics

A major research challenge of multi-robot systems is to predict the emerging behaviors from the local interactions of the individual agents. Biological systems can generate robust and complex behaviors through relatively simple local interactions in a world characterized by rapid changes, high uncertainty, infinite richness, and limited availability of information. Gene Regulatory Networks (GRNs) play a central role in understanding natural evolution and development of biological organisms from cells. In this paper, inspired by biological organisms, we propose a distributed GRN-based algorithm for a multi-robot construction task. Through this algorithm, multiple robots can self-organize autonomously into different predefined shapes, and self-reorganize adaptively under dynamic environments. This developmental process is evolved using a multi-objective optimization algorithm to achieve a shorter travel distance and less convergence time. Furthermore, a theoretical proof of the system's convergence is also provided. Various case studies have been conducted in the simulation, and the results show the efficiency and convergence of the proposed method.

A cellular mechanism for multi-robot construction via evolutionary multi-objective optimization of a gene regulatory network.

Most existing multirobot systems for pattern formation rely on a predefined pattern, which is impractical for dynamic environments where the pattern to be formed should be able to change as the environment changes. In addition, adaptation to environmental changes should be realized based only on local perception of the robots. In this paper, we propose a hierarchical gene regulatory network (H-GRN) for adaptive multirobot pattern generation and formation in changing environments. The proposed model is a two-layer gene regulatory network (GRN), where the first layer is responsible for adaptive pattern generation for the given environment, while the second layer is a decentralized control mechanism that drives the robots onto the pattern generated by the first layer. An evolutionary algorithm is adopted to evolve the parameters of the GRN subnetwork in layer 1 for optimizing the generated pattern. The parameters of the GRN in layer 2 are also optimized to improve the convergence performance. Simulation results demonstrate that the H-GRN is effective in forming the desired pattern in a changing environment. Robustness of the H-GRN to robot failure is also examined. A proof-of-concept experiment using e-puck robots confirms the feasibility and effectiveness of the proposed model.

/pdf/a-hierarchical-gene-regulatory-network-for-adaptive-3velzjzjn7.pdf

A Hierarchical Gene Regulatory Network for Adaptive Multirobot Pattern Formation

In this paper, we present a two-layer hierarchical mechanochemical model for self-reconfiguration of modular robots in changing environments. The model, which is inspired by the embryonic development of multi-cellular organisms and chemical morphogenesis, can autonomously generate and form different patterns for modular robots to adapt to environmental changes. Layer 1 of the model utilizes a virtual-cell based mechanochemical model to generate appropriate target patterns (i.e., chemical blueprints) for current environment. Layer 2 is a gene regulatory network (GRN) based controller to -coordinate the modules of modular robots for physically realizing the chemical target pattern defined by the first layer. This hierarchical mechanochemical framework is a distributed system in that each module makes decisions based on its local perceptions. To optimize pattern de-sign of modular robots, the covariance matrix adaptation evolution strategy (CMA-ES) is adopted to evolve the pattern parameters of the mechanochemical model. Simulation results demonstrate that the proposed system is effective and robust in autonomously reconfiguring modular robots to adapt to environmental changes.

Yan Meng

Papers

Autonomous robot calibration using vision technology

Morphogenetic Robotics: An Emerging New Field in Developmental Robotics

A cellular mechanism for multi-robot construction via evolutionary multi-objective optimization of a gene regulatory network.

A Hierarchical Gene Regulatory Network for Adaptive Multirobot Pattern Formation

Autonomous Self-Reconfiguration of Modular Robots by Evolving a Hierarchical Mechanochemical Model