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

Deep learning in neural networks

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Statistical physics has proven to be a fruitful framework to describe phenomena outside the realm of traditional physics. Recent years have witnessed an attempt by physicists to study collective phenomena emerging from the interactions of individuals as elementary units in social structures. A wide list of topics are reviewed ranging from opinion and cultural and language dynamics to crowd behavior, hierarchy formation, human dynamics, and social spreading. The connections between these problems and other, more traditional, topics of statistical physics are highlighted. Comparison of model results with empirical data from social systems are also emphasized.

Statistical physics of social dynamics

This paper presents a novel adaptive synthetic (ADASYN) sampling approach for learning from imbalanced data sets. The essential idea of ADASYN is to use a weighted distribution for different minority class examples according to their level of difficulty in learning, where more synthetic data is generated for minority class examples that are harder to learn compared to those minority examples that are easier to learn. As a result, the ADASYN approach improves learning with respect to the data distributions in two ways: (1) reducing the bias introduced by the class imbalance, and (2) adaptively shifting the classification decision boundary toward the difficult examples. Simulation analyses on several machine learning data sets show the effectiveness of this method across five evaluation metrics.

/pdf/adasyn-adaptive-synthetic-sampling-approach-for-imbalanced-50dp5u9x3j.pdf

ADASYN: Adaptive synthetic sampling approach for imbalanced learning

https://users.dimi.uniud.it/~antonio.dangelo/Robotica/2012/helper/leggedRobot/Ijspeert08NN.pdf

2008 Special Issue: Central pattern generators for locomotion control in animals and robots: A review

From Animals to Animats

The Animals to Animats Conference brings together researchers from ethology, psychology, ecology, artificial intelligence, artificial life, robotics, engineering, and related fields to further understanding of the behaviors and underlying mechanisms that allow natural and synthetic agents (animats) to adapt and survive in uncertain environments. The work presented focuses on well-defined models--robotic, computer-simulation, and mathematical--that help to characterize and compare various organizational principles or architectures underlying adaptive behavior in both natural animals and animats.

http://www.gbv.de/dms/ilmenau/toc/219040818maes.PDF

From Animals to Animats 10

IEEE International Joint Conference on Neural Networks

A methodology for optimizing player satisfaction in games on the "playware" physical interactive platform is demonstrated in this paper. Previously constructed artificial neural network user models, reported in the literature, map individual playing characteristics to reported entertainment preferences for augmented-reality game players. An adaptive mechanism then adjusts controllable game parameters in real time in order to improve the entertainment value of the game for the player. The basic approach presented here applies gradient ascent to the user model to suggest the direction of parameter adjustment that leads toward games of higher entertainment value. A simple rule set exploits the derivative information to adjust specific game parameters to augment the entertainment value. Those adjustments take place frequently during the game with interadjustment intervals that maintain the user model's accuracy. Performance of the adaptation mechanism is evaluated using a game survey experiment. Results indicate the efficacy and robustness of the mechanism in adapting the game according to a user's individual playing features and enhancing the gameplay experience. The limitations and the use of the methodology as an effective adaptive mechanism for entertainment capture and augmentation are discussed.

/pdf/real-time-game-adaptation-for-optimizing-player-satisfaction-19lqiljyn8.pdf

Real-Time Game Adaptation for Optimizing Player Satisfaction

Mainly motivated by the current lack of a qualitative and quantitative entertainment formulation of computer games and the procedures to generate it, this article covers the following issues: It presents the features-extracted primarily from the opponent behavior-that make a predator/prey game appealing; provides the qualitative and quantitative means for measuring player entertainment in real time, and introduces a successful methodology for obtaining games of high satisfaction. This methodology is based on online (during play) learning opponents who demonstrate cooperative action. By testing the game against humans, we confirm our hypothesis that the proposed entertainment measure is consistent with the judgment of human players. As far as learning in real time against human players is concerned, results suggest that longer games are required for humans to notice some sort of change in their entertainment.

http://yannakakis.net/wp-content/uploads/2012/02/AAI.pdf

John Hallam

Papers

From Animals to Animats

From Animals to Animats 10

IEEE International Joint Conference on Neural Networks

Real-Time Game Adaptation for Optimizing Player Satisfaction

Towards optimizing entertainment in computer games