This paper describes NETtalk, a class of massively-parallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed human performance. (i) The learning follows a power law. (;i) The more words the network learns, the better it is at generalizing and correctly pronouncing new words, (iii) The performance of the network degrades very slowly as connections in the network are damaged: no single link or processing unit is essential. (iv) Relearning after damage is much faster than learning during the original training. (v) Distributed or spaced practice is more effective for long-term retention than massed practice. Network models can be constructed that have the same performance and learning characteristics on a particular task, but differ completely at the levels of synaptic strengths and single-unit responses. However, hierarchical clustering techniques applied to NETtalk reveal that these different networks have similar internal representations of letter-to-sound correspondences within groups of processing units. This suggests that invariant internal representations may be found in assemblies of neurons intermediate in size between highly localized and completely distributed representations.

This paper examines whether temporal difference methods for training connectionist networks, such as Suttons's TD(lambda) algorithm can be successfully applied to complex real-world problems. A number of important practical issues are identified and discussed from a general theoretical perspective. These practical issues are then examined in the context of a case study in which TD(lambda) is applied to learning the game of backgammon from the outcome of self-play. This is apparently the first application of this algorithm to a complex nontrivial task. It is found that, with zero knowledge built in, the network is able to learn from scratch to play the entire game at a fairly strong intermediate level of performance which is clearly better than conventional commercial programs and which in fact surpasses comparable networks trained on a massive human expert data set. This indicates that TD learning may work better in practice than one would expect based on current theory, and it suggests that further analysis of TD methods, as well as applications in other complex domains may be worth investigating.

Neural networks, despite their empirically-proven abilities, have been little used for the refinement of existing knowledge because this task requires a three-step process. First, knowledge in some form must be inserted into a neural network. Second, the network must be refined. Third, knowledge must be extracted from the network. We have previously described a method for the first step of this process. Standard neural learning techniques can accomplish the second step. In this paper, we propose and empirically evaluate a method for the final, and possibly most difficult, step. This method efficiently extracts symbolic rules from trained neural networks. The four major results of empirical tests of this method are that the extracted rules: (1) closely reproduce (and can even exceed) the accuracy of the network from which they are extracted; (2) are superior to the rules produced by methods that directly refine symbolic rules; (3) are superior to those produced by previous techniques fo...

Abstract Despite the fact that many symbolic and neural network (connectionist) learning algorithms address the same problem of learning from classified examples, very little is known regarding their comparative strengths and weaknesses. Experiments comparing the ID3 symbolic learning algorithm with the perception and backpropagation neural learning algorithms have been performed using five large, real-world data sets. Overall, backpropagation performs slightly better than the other two algorithms in terms of classification accuracy on new examples, but takes much longer to train. Experimental results suggest that backpropagation can work significantly better on data sets containing numerical data. Also analyzed empirically are the effects of (1) the amount of training data, (2) imperfect training examples, and (3) the encoding of the desired outputs. Backpropagation occasionally outperforms the other two systems when given relatively small amounts of training data. It is slightly more accurate than ID3 when examples are noisy or incompletely specified. Finally, backpropagation more effectively utilizes a "distributed " output encoding.

Abstract not found

Since the beginning of AI, mind games have been studied as relevant application fields. Nowadays, some programs are better than human players in most classical games. Their results highlight the efficiency of AI methods that are now quite standard. Such methods are very useful to Go programs, but they do not enable a strong Go program to be built. The problems related to Computer Go require new AI problem solving methods. Given the great number of problems and the diversity of possible solutions, Computer Go is an attractive research domain for AI. Prospective methods of programming the game of Go will probably be of interest in other domains as well. The goal of this paper is to present Computer Go by showing the links between existing studies on Computer Go and different AI related domains: evaluation function, heuristic search, machine learning, automatic knowledge generation, mathematical morphology and cognitive science. In addition, this paper describes both the practical aspects of Go programming, such as program optimization, and various theoretical aspects such as combinatorial game theory, mathematical morphology, and MonteCarlo methods. B. Bouzy T. Cazenave page 2 08/06/01 1.

Machine learning is an area where both symbolic and neural approaches have been heavily investigated. However, there has been little research into the synergies achievable by combining these two learning paradigms. A hybrid approach that combines the symbolically-oriented explanation-based learning paradigm with the neural back-propagation algorithm is described. Most realistic problems can never be formalized exactly. However, there is much to be gained by utilizing the capability to reason nearly correctly. In the presented EBL-ANN algorithm, a "roughly-correct" explanatory capability leads to the acquisition of a classification rule that is almost correct. The rule is mapped into a neural network, where subsequent refinement improves it. This approach overcomes problems that arise when using imperfect domain theories to build explanations and addresses the problem of choosing a good initial neural network configuration. Empirical results show that the hybrid system more accurately l...

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

This paper demonstrates how the nature of the opposition during training affects learning to play two-person, perfect information board games. It considers different kinds of competitive training, the impact of trainer error, appropriate metrics for post-training performance measurement, and the ways those metrics can be applied. The results suggest that teaching a program by leading it repeatedly through the same restricted paths, albeit high quality ones, is overly narrow preparation for the variations that appear in real-world experience. The results also demonstrate that variety introduced into training by random choice is unreliable preparation, and that a program that directs its own training may overlook important situations. The results argue for a broad variety of training experience with play at many levels. This variety may either be inherent in the game or introduced deliberately into the training. Lesson and practice training, a blend of expert guidance and knowledge-based, self-directed elaboration, is shown to be particularly effective for learning during competition. Key words: training, competition, game playing, reliability 1.

The method of temporal differences (TD) is a learning technique which specialises in predicting the likely outcome of a sequence over time. Examples of such sequences include speech frame vectors, whose outcome is a phoneme or word decision, and positions in a board game, whose outcome is a win/loss decision. Recent results by Tesauro in the domain of backgammon indicate that a neural network, trained by TD methods to evaluate positions generated by self-play, can reach an advanced level of backgammon skill. For my summer thesis project, I first implemented the TD/neural network learning algorithms and confirmed Tesauro's results, using the domains of tic-tac-toe and backgammon. Then, motivated by Waibel's success with modular neural networks for phoneme recognition, I experimented with using two modular architectures (DDD and Meta-Pi) in place of the monolithic networks. I found that using the modular networks significantly enhanced the ability of the backgammon evaluator to change it...