Model Neural Networks And Behavior

How can we make better sense of animal behavior by using what we know about the brain? This is the first book that attempts to answer this important question by applying neural network theory. Scientists create Artificial Neural Networks (ANNs) to make models of the brain. These networks mimic the architecture of a nervous system by connecting elementary neuron-like units into networks in which they stimulate or inhibit each other's activity in much the same way neurons do. This book shows how scientists can employ ANNs to analyze animal behavior, explore the general principles of the nervous systems, and test potential generalizations among species. The authors focus on simple neural networks to show how ANNs can be investigated by math and by computers. They demonstrate intuitive concepts that make the operation of neural networks more accessible to nonspecialists. The first chapter introduces various approaches to animal behavior and provides an informal introduction to neural networks, their history, and their potential advantages. The second chapter reviews artificial neural networks, including biological foundations, techniques, and applications. The following three chapters apply neural networks to such topics as learning and development, classical instrumental condition, and the role of genes in building brain networks. The book concludes by comparing neural networks to other approaches. It will appeal to students of animal behavior in many disciplines. It will also interest neurobiologists, cognitive scientists, and those from other fields who wish to learn more about animal behavior.

This volume is part of the two-volume proceedings of the 19th International Conf- ence on Artificial Neural Networks (ICANN 2009), which was held in Cyprus during September 14–17, 2009. The ICANN conference is an annual meeting sp- sored by the European Neural Network Society (ENNS), in cooperation with the - ternational Neural Network Society (INNS) and the Japanese Neural Network Society (JNNS). ICANN 2009 was technically sponsored by the IEEE Computational Intel- gence Society. This series of conferences has been held annually since 1991 in various European countries and covers the field of neurocomputing, learning systems and related areas. Artificial neural networks provide an information-processing structure inspired by biological nervous systems. They consist of a large number of highly interconnected processing elements, with the capability of learning by example. The field of artificial neural networks has evolved significantly in the last two decades, with active partici- tion from diverse fields, such as engineering, computer science, mathematics, artificial intelligence, system theory, biology, operations research, and neuroscience. Artificial neural networks have been widely applied for pattern recognition, control, optimization, image processing, classification, signal processing, etc.

The most conspicuous function of the nervous system is to control animal behav ior. From the complex operations of learning and mentation to the molecular con figuration of ionic channels, the nervous system serves as the interface between an animal and its environment. To study and understand the fundamental mecha nisms underlying the control of behavior, it is often both necessary and desirable to employ biological systems with characteristics especially suitable for answering specific questions. In neurobiology, many invertebrates have become established as model systems for investigations at both the systems and the cellular level. Large, readily identifiable neurons have made invertebrates especially useful for cellular studies. The fact that these neurons occur in much smaller numbers than those in higher animals also makes them important for circuit analysis. Although important differences exist, some of the questions that would be tech nically impossible to answer with vertebrates can become experimentally tractable with invertebrates.

The most conspicuous function of the nervous system is to control animal behav ior. From the complex operations of learning and mentation to the molecular con figuration of ionic channels, the nervous system serves as the interface between an animal and its environment. To study and understand the fundamental mecha nisms underlying the control of behavior, it is often both necessary and desirable to employ biological systems with characteristics especially suitable for answering specific questions. In neurobiology, many invertebrates have become established as model systems for investigations at both the systems and the cellular level. Large, readily identifiable neurons have made invertebrates especially useful for cellular studies. The fact that these neurons occur in much smaller numbers than those in higher animals also makes them important for circuit analysis. Although important differences exist, some of the questions that would be tech nically impossible to answer with vertebrates can become experimentally tractable with invertebrates.

How can we make better sense of animal behavior by using what we know about the brain? This is the first book that attempts to answer this important question by applying neural network theory. Scientists create Artificial Neural Networks (ANNs) to make models of the brain. These networks mimic the architecture of a nervous system by connecting elementary neuron-like units into networks in which they stimulate or inhibit each other's activity in much the same way neurons do. This book shows how scientists can employ ANNs to analyze animal behavior, explore the general principles of the nervous systems, and test potential generalizations among species. The authors focus on simple neural networks to show how ANNs can be investigated by math and by computers. They demonstrate intuitive concepts that make the operation of neural networks more accessible to nonspecialists. The first chapter introduces various approaches to animal behavior and provides an informal introduction to neural networks, their history, and their potential advantages. The second chapter reviews artificial neural networks, including biological foundations, techniques, and applications. The following three chapters apply neural networks to such topics as learning and development, classical instrumental condition, and the role of genes in building brain networks. The book concludes by comparing neural networks to other approaches. It will appeal to students of animal behavior in many disciplines. It will also interest neurobiologists, cognitive scientists, and those from other fields who wish to learn more about animal behavior.

This textbook provides a general introduction to the field of neural networks. Thoroughly revised and updated from the previous editions of 1991 and 2000, the current edition concentrates on networks for modeling brain processes involved in cognitive and behavioral functions. Part one explores the philosophy of modeling and the field’s history starting from the mid-1940s, and then discusses past models of associative learning and of short-term memory that provide building blocks for more complex recent models. Part two of the book reviews recent experimental findings in cognitive neuroscience and discusses models of conditioning, categorization, category learning, vision, visual attention, sequence learning, behavioral control, decision making, reasoning, and creativity. The book presents these models both as abstract ideas and through examples and concrete data for specific brain regions. The book includes two appendices to help ground the reader: one reviewing the mathematics used in network modeling, and a second reviewing basic neuroscience at both the neuron and brain region level. The book also includes equations, practice exercises, and thought experiments.

In this advanced text, the author, starting with the simple assumption that psychological associations are represented by the strength of synaptic connections, details several mechanistic descriptions of complex cognitive behaviors. Part I presents neural network theories of classical conditioning; Part II describes neural networks of operant conditioning, and animal communication; Part III discusses spatial and cognitive mapping, and finally, Part IV shows how neural network models permit one to simultaneously develop psychological theories and models of the brain. The book includes computer software that allows the computer simulation of classical conditioning and the effect of different brain lesions on many classical paradigms. All those people interested in neural networks, from psychologists, through neuroscientists to computer scientists working on artificial intelligence and robotics, will find this book an excellent advanced guide to the subject.

Recent advances in motor behavior research rely on detailed knowledge of the characteristics of the neurons and networks that generate motor behavior. At the cellular level, Neurons, Networks, and Motor Behavior describes the computational characteristics of individual neurons and how these characteristics are modified by neuromodulators. At the network and behavioral levels, the volume discusses how network structure is dynamically modulated to produce adaptive behavior. Comparisons of model systems throughout the animal kingdom provide insights into general principles of motor control. Contributors describe how networks generate such motor behaviors as walking, swimming, flying, scratching, reaching, breathing, feeding, and chewing. An emerging principle of organization is that nervous systems are remarkably efficient in constructing neural networks that control multiple tasks and dynamically adapt to change.The volume contains six sections: selection and initiation of motor patterns; generation and formation of motor patterns: cellular and systems properties; generation and formation of motor patterns: computational approaches; modulation and reconfiguration; short-term modulation of pattern generating circuits; and sensory modification of motor output to control whole body orientation.

Behavior Analysis with Machine Learning Using R introduces machine learning and deep learning concepts and algorithms applied to a diverse set of behavior analysis problems. It focuses on the practical aspects of solving such problems based on data collected from sensors or stored in electronic records. The included examples demonstrate how to perform common data analysis tasks such as: data exploration, visualization, preprocessing, data representation, model training and evaluation. All of this, using the R programming language and real-life behavioral data. Even though the examples focus on behavior analysis tasks, the covered underlying concepts and methods can be applied in any other domain. No prior knowledge in machine learning is assumed. Basic experience with R and basic knowledge in statistics and high school level mathematics are beneficial. Features: Build supervised machine learning models to predict indoor locations based on WiFi signals, recognize physical activities from smartphone sensors and 3D skeleton data, detect hand gestures from accelerometer signals, and so on. Program your own ensemble learning methods and use Multi-View Stacking to fuse signals from heterogeneous data sources. Use unsupervised learning algorithms to discover criminal behavioral patterns. Build deep learning neural networks with TensorFlow and Keras to classify muscle activity from electromyography signals and Convolutional Neural Networks to detect smiles in images. Evaluate the performance of your models in traditional and multi-user settings. Build anomaly detection models such as Isolation Forests and autoencoders to detect abnormal fish behaviors. This book is intended for undergraduate/graduate students and researchers from ubiquitous computing, behavioral ecology, psychology, e-health, and other disciplines who want to learn the basics of machine learning and deep learning and for the more experienced individuals who want to apply machine learning to analyze behavioral data.