Inductive concept learning is the task of learning to assign cases to a discrete set of classes. In real-world applications of concept learning, there are many different types of cost involved. The majority of the machine learning literature ignores all types of cost (unless accuracy is interpreted as a type of cost measure). A few papers have investigated the cost of misclassification errors. Very few papers have examined the many other types of cost. In this paper, we attempt to create a taxonomy of the different types of cost that are involved in inductive concept learning. This taxonomy may help to organize the literature on cost-sensitive learning. We hope that it will inspire researchers to investigate all types of cost in inductive concept learning in more depth. 1.

In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could learn through interacting with the player, behavior could improve as the game is played, keeping it interesting. This paper introduces the real-time NeuroEvolution of Augmenting Topologies (rtNEAT) method for evolving increasingly complex artificial neural networks in real time, as a game is being played. The rtNEAT method allows agents to change and improve during the game. In fact, rtNEAT makes possible an entirely new genre of video games in which the player trains a team of agents through a series of customized exercises. To demonstrate this concept, the NeuroEvolving Robotic Operatives (NERO) game was built based on rtNEAT. In NERO, the player trains a team of virtual robots for combat against other players ’ teams. This paper describes results from this novel application of machine learning, and demonstrates that rtNEAT makes possible video games like NERO where agents evolve and adapt in real time. In the future, rtNEAT may allow new kinds of educational and training applications through interactive and adapting games. 1

The past two decades have seen rapid advances in high performance computing and

Evolutionary algorithms have been appied to the synthesis of neural architectures...

Knowledge based artificial neural networks offer an approach for connectionist theory refinement. We present an algorithm for refining and extending the domain theory incorporated in a knowledge based neural network using constructive neural network learning algorithms. The initial domain theory comprising of propositional rules is translated into a knowledge based network of threshold logic units (TLU). The domain theory is modified by dynamically adding neurons to the existing network. A constructive neural network learning algorithm is used to add and train these additional neurons using a sequence of labeled examples. We propose a novel hybrid constructive learning algorithm based on the Tiling and Pyramid constructive learning algorithms that allows knowledge based neural network to handle patterns with continuous valued attributes. Results of experiments on two non-trivial tasks (the ribosome binding site prediction and the financial advisor) show that our algorithm compares favo...

This paper presents new techniques for biosequence classification, with a focus on recognizing E. Coli promoters in DNA. Specifically, given an unlabeled DNA sequence S, we want to determine whether or not S is an E. Coli promoter. We use an expectation-maximization (EM) algorithm to locate the-35 and-10 binding sites in an E. Coli promoter sequence. The EM algorithm differs from previously published EM algorithms in that, instead of assuming a uniform distribution for the lengths of the spacer between the-35 binding site and the-10 binding site as well as the spacer between the-10 binding site and the transcriptional start site, our algorithm deduces the probability distribution for these lengths. Based on the located binding sites, we select features in each E. Coli promoter sequence according to their information contents and represent the features using an orthogonal encoding method. We then feed the features to a neural network for promoter recognition. Empirical studies show that the proposed approach achieves good performance on different datasets.

The specification and management of requirements is widely considered to be one of the most important yet most problematic phases in software engineering. In some applications, such as in safety critical areas or knowledge-based systems, the construction of a requirements domain theory is regarded as an important part of this phase. Building and maintaining such a domain theory, however, requires a large investment and a range of powerful validation and maintenance tools. The area of `theory refinement' is concerned with the use of training data to automatically change an existing theory so that it better fits the data. Theory refinement techniques have not been extensively used in applications because of the problems in scaling up their underlying algorithms. In this paper we describe an environment for validating and maintaining a requirements domain theory written in a customised form of many-sorted logic. The environment has been used for several years to maintain a theo...

. Knowledge based artificial neural networks offer an attractive approach to extending or modifying incomplete knowledge bases or domain theories through a process of data-driven theory refinement. We present an efficient algorithm for data-driven knowledge discovery and theory refinement using DistAl, a novel (inter-pattern distance based, polynomial time) constructive neural network learning algorithm. The initial domain theory comprising of propositional rules is translated into a knowledge based network. The domain theory is modified using DistAl which adds new neurons to the existing network as needed to reduce classification errors associated with the incomplete domain theory on labeled training examples. The proposed algorithm is capable of handling patterns represented using binary, nominal, as well as numeric (real-valued) attributes. Results of experiments on several datasets for financial advisor and the human genome project indicate that the performance of th...

Research emanating from Artificial Intelligence has throughout its history contributed to techniques and ideas in Software Engineering. We describe in this paper a case study showing the use of theory revision to the refinement of a formally specified requirements model. In a previous project we were contracted to create a precise model of the complex criteria governing the separation of aircraft profiles in Atlantic Airspace. During that work it became clear that the (automated) validation of the model was of the utmost importance, and in our current project we have used machine learning tools to provide extra support in bug identification, bug removal and maintenance of such a requirements model. In this paper we give an overview of the domain, identify a relevant learning bias which makes search for revisions tractable, and describe a systematic approach for the application of theory revision to such a model. We illustrate the approach with results of experiments where theory revisi...

A major goal for AI is to allow users to interact with agents that learn in real time, making new kinds of interactive simulations, training applications, and digital entertainment possible. This paper describes such a learning technology, called real-time NeuroEvolution of Augmenting Topologies (rtNEAT), and describes how rtNEAT was used to build the NeuroEvolving Robotic Operatives (NERO) video game. This game represents a new genre of machine learning games where the player trains agents in real time to perform challenging tasks in a virtual environment. Providing laymen the capability to effectively train agents in real time with no prior knowledge of AI or machine learning has broad implications, both in promoting the field of AI and making its achievements accessible to the public at large.