1996 | | | **Review of Inductive Logic Programming: Techniques and Applications by Nada Lavrac, Saso Dzeroski** - *Michael Pazzani* |

| | | **Real-World Robotics: Learning to Plan for Robust Execution** - *Scott W. Bennett and Gerald F. DeJong* |

| | | **Background knowledge in GA-based concept learning** - *Jukka Hekanaho* |

| | | **Nonparametric statistical methods for experimental evaluations of speedup learning** - *Geoffrey J. Gordon and Alberto Maria Segre* |

| | | **Simplified support vector decision rules** - *Chris J. C. Burges* |

| | | **Learning Concepts from Sensor Data of a Mobile Robot** - *Volker Klingspor, Katharina J. Morik and Anke D. Rieger* |

| | | **A simple algorithm for learning O log n -term DNF** - *Eyal Kushilevitz* |

| | | **Elementary formal systems, intrinsic complexity, and procrastination** - *Sanjay Jain and Arun Sharma* |

| | | **Experiments with a new Boosting algorithm** - *Yoav Freund and Robert E. Schapire* |

| | | **Graph learning with a nearest neighbor approach** - *Sven Koenig and Yury Smirnov* |

| | | **Learning an optimal decision strategy in an influence diagram with latent variables** - *V. G. Vovk* |

| | | **Efficient Learning of One-Variable Pattern Languages from Positive Examples** - *T. Erlebach, P. Rossmanith, H. Stadtherr, A. Steger and T. Zeugmann* |

| | | **Learning of depth two neural networks with constant fan-in at the hidden nodes** - *Peter Auer, Stephen Kwek, Wolfgang Maass and Manfred K. Warmuth* |

| | | **On learning width two branching programs** - *Nader H. Bshouty, Christino Tamon and David K. Wilson* |

| | | **Applying winnow to context-sensitive spelli ng correction** - *Andrew R. Golding and Dan Roth* |

| | | **The dual DFA learning problem: hardness results for programming by demonstration and learning first-order representations** - *William W. Cohen* |

| | | **On Learning Visual Concepts and DNF Formulae** - *Eyal Kushilevitz and Dan Roth* |

| | | **Learning to Select Useful Landmarks** - *Russell Greiner and Ramana Isukapalli* |

| | | **Book review: inductive logic programming: techniques and applications** - *Michael Pazzani* |

| | | **Efficient learning of selective Bayesian network classifiers** - *Moninder Singh and Gregory M. Provan* |

| | | **Experimental knowledge acquisition for planning** - *Kang Soo Tae and Diane J. Cook* |

| | | **VC dimension of an integrate-and-fire neuron model** - *Anthony M. Zador and Barak A. Pearlmutter* |

| | | **CLASSIC Learning** - *Michael Frazier and Leonard Pitt* |

| | | **Feature-Based Methods for Large Scale Dynamic Programming** - *John N. Tsitsiklis and Benjamin van Roy* |

| | | **Approximating value trees in structured dynamic programming** - *Craig Boutilier and Richard Dearden* |

| | | **Scaling Up Inductive Learning with Massive Parallelism** - *Foster John Provost and John M. Aronis* |

| | | **On the Intrinsic Complexity of Learning** - *R. Freivalds, E. Kinber and C. Smith* |

| | | **Analysis of greedy expert hiring and an application to memory-based learning** - *Igal Galperin* |

| | | **Towards robust model selection using estimation and approximation error bounds** - *Joel Ratsaby, Ronny Meir and Vitaly Maiorov* |

| | | **Algorithms and applications for multitask learning** - *Rich Caruana* |

| | | **Technical note: incremental multi-step Q-learning** - *Jing Peng and Ronald J. Williams* |

| | | **Learning Controllers for Industrial Robots** - *C. Baroglio, A. Giordana, M. Kaiser, M. Nuttin and R. Piola* |

| | | **Learning branches and learning to win closed games** - *Martin Kummer and Matthias Ott* |

| | | **Angluin’s theorem for indexed families of r.e. sets and applications** - *Dick de Jongh and Makoto Kanazawa* |

| | | **Learning binary perceptrons perfectly efficiently** - *Shao C. Fang and Santosh S. Venkatesh* |

| | | **Exploration Bonuses and Dual Control** - *Peter Dayan and Terrence J. Sejnowski* |

| | | **Scaling up average reward reinforcement learning by approximating the domain models and the value function** - *Prasad Tadepalli and DoKyeong Ok* |

| | | **Searching for structure in multiple streams of data** - *Tim Oates and Paul R. Cohen* |

| | | **On-line adaptation of a signal predistorter through dual reinforcement learning** - *Patrick Goetz, Shailesh Kumar and Risto Miikkulainen* |

| | | **Efficient Reinforcement Learning through Symbiotic Evolution** - *David E. Moriarty and Risto Miikkulainen* |

| | | **Efficient Incremental Induction of Decision Trees** - *Dimitrios Kalles and Tim Morris* |

| | | **A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns** - *Sally A. Goldman and Stephen D. Scott* |

| | | **Non mean square error criteria for the training of learning machines** - *Marco Saerens* |

| | | **Teaching a smarter learner** - *Sally A. Goldman and H. David Mathias* |

| | | **A Bayesian/information theoretic model of bias learning** - *Jonathan Baxter* |

| | | **representing and learning quality-improving search control knowledge** - *M. Alicia Pérez* |

| | | **Introduction** - *Judy A. Franklin, Tom M. Mitchell and Sebastian Thrun* |

| | | **Recognition and exploitation of contextual clues via incremental meta-learning** - *Gerhard Widmer* |

| | | **The Power of Amnesia: Learning Probabilistic Automata with Variable Memory Length** - *Dana Ron, Yoram Singer and Naftali Tishby* |

| | | **Monotonic and dual monotonic language learning** - *S. Lange, T. Zeugmann and S. Kapur* |

| | | **The importance of convexity in learning with squared loss** - *Wee Sun Lee, Peter L. Bartlett and Robert C. Williamson* |

| | | **Probabilistic instance-based learning** - *Henry Tirri, Petri Kontkanen and Petri Myllymäki* |

| | | **Improving the efficiency of knowledge base refinement** - *Leonardo Carbonara and Derek Sleeman* |

| | | **Active Learning for Vision-Based Robot Grasping** - *Marcos Salganicoff, Lyle H. Ungar and Ruzena Bajcsy* |

| | | **A probabilistic approach to feature selection - a filter solution** - *Huan Liu and Rudy Setiono* |

| | | **Unsupervised learning using MML** - *Jonathan J. Oliver, Rohan A. Baxter and Chris S. Wallace* |

| | | **Probabilistic and team PFIN-type learning: general properties** - *Andris Ambainis* |

| | | **Learning word association norms using tree cut pair models** - *Naoki Abe and Hang Li* |

| | | **Synthesizing enumeration techniques for language learning** - *Ganesh R. Baliga, John Case and Sanjay Jain* |

| | | **On-line Prediction and Conversion Strategies** - *Nicolo Cesa-Bianchi, Yoav Freund, David P. Helmbold and Manfred K. Warmuth* |

| | | **Worst-Case Loss Bounds for Sigmoided Linear Neurons** - *D. P. Helmbold, J. Kivinen and M. K. Warmuth* |

| | | **Learning goal oriented Bayesian networks for telecommunications risk management** - *Kazuo J. Ezawa, Moninder Singh and Steven W. Norton* |

| | | **Incremental Multi-Step Q-Learning** - *Jing Peng and Ronald J. Williams* |

| | | **A Reply to Pazzani’s Book Review of Inductive Logic Programming: Techniques and Applications** - *Nada Lavrac and Saso Dzeroski* |

| | | **Analysis of a simple learning algorithm: learning foraging thresholds for lizards** - *Leslie Ann Goldberg, William E. Hart and David Bruce Wilson* |

| | | **Learning evaluation functions for large acyclic domains** - *Justin A. Boyan and Andrew W. Moore* |

| | | **Relational instance-based learning** - *Werner Emde and Dietrich Wettschereck* |

| | | **A convergent reinforcement learning algorithm in the continuous case: the finite-element reinforcement learning** - *Rémi Munos* |

| | | **Learning changing concepts by exploiting the structure of change** - *Peter L. Bartlett, Shai Ben-David and Sanjeev R. Kulkarni* |

| | | **Identifying the information contained in a flawed theory** - *Sean P. Engelson and Moshe Koppel* |

| | | **Negative robust learning results for Horn clause programs** - *Pascal Jappy, Richard Nock and Olivier Gascuel* |

| | | **Delaying the choice of bias: a disjunctive version space approach** - *Michele Sebag* |

| | | **Second tier for decision trees** - *Miroslav Kubat* |

| | | **Solving POMDPs with Levin search and EIRA** - *Marco Wiering and Jürgen Scmidhuber* |

| | | **Noise-Tolerant Distribution-Free Learning of General Geometric Concepts** - *Bshouty, Goldman, Mathias, Suri and Tamaki* |

| | | **Learning Bayesian belief networks based on the minimum description length principle: an efficient algorithm using the B \& B technique** - *Joe Suzuki* |

| | | **Non-linear decision trees - NDT** - *Andreas Ittner and Michael Schlosser* |

| | | **Co-Learning of Recursive Languages from Positive Data** - *R. Freivalds and T. Zeugmann* |

| | | **Linear least-squares algorithms for temporal difference learning** - *Steven J. Bradtke and Andrew G. Barto* |

| | | **PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples** - *Philip M. Long and Lei Tan* |

| | | **Learning despite concept variation by finding structure in attribute-based data** - *Eduardo Pérez and Larry A. Rendell* |

| | | **Discovering structure in multiple learning tasks: the TC algorithm** - *Sebastian Thrun and Joseph O’Sullivan* |

| | | **BEXA: A Covering Algorithm for Learning Propositional Concept Descriptions** - *Hendrik Theron and Ian Cloete* |

| | | **The loss from imperfect value functions in expectation-based and minimax-based tasks** - *Matthias Heger* |

| | | **Performance Improvement of Robot Continuous-Path Operation through Iterative Learning Using Neural Networks** - *Peter C. Y. Chen, James K. Mills and Kenneth C. Smith* |

| | | **Exploiting the omission of irrelevant data** - *Russell Greiner, Adam J. Grove and Alexander Kogan* |

| | | **Statistical theory of generalization abstract** - *Vladimir Vapnik* |

| | | **Asking questions to minimize errors** - *Nader H. Bshouty, Sally A. Goldman, Thomas R. Hancock and Sleiman Matar* |

| | | **Analogy access by mapping spreading and abstraction in large, multifunctional knowledge bases** - *Davide Roverso* |

| | | **PAC Learning of One-Dimensional Patterns** - *Paul W. Goldberg, Sally A. Goldman and Stephen D. Scott* |

| | | **Reinforcement Learning with Replacing Eligibility Traces** - *Satinder P Singh and Richard S. Sutton* |

| | | **Passive distance learning for robot navigation** - *Sven Koenig and Reid G. Simmons* |

| | | **General bounds on the number of examples needed for learning probabilistic concepts** - *Hans Ulrich Simon* |

| | | **Learning by Erasing** - *S. Lange, R. Wiehagen and T. Zeugmann* |

| | | **Predicting a binary sequence almost as well as the optimal biased coin** - *Yoav Freund* |

| | | **Representation changes for efficient learning in structural domains** - *Jean-Daniel Zucker and Jean-Gabriel Ganascia* |

| | | **Data mining and machine learning abstract** - *Heikki Mannila* |

| | | **A framework for structural risk minimization** - *John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson and Martin Anthony* |

| | | **Editorial on new Machine Learning website** - *Thomas G. Dietterich* |

| | | **Actual return reinforcement learning versus temporal differences: some theoretical and experimental results** - *Mark D. Pendrith and Malcolm R. K. Ryan* |

| | | **Reinforcement learning in factories: the auton project abstract** - *Andrew W. Moore* |

| | | **Theory-guided empirical speedup learning of goal decomposition rules** - *Chandra Reddy, Prasad Tadepalli and Silvana Roncagliolo* |

| | | **Learning curve bounds for a Markov decision process with undiscounted rewards** - *Lawrence K. Saul and Satinder P. Singh* |

| | | **Incremental Learning from Positive Data** - *S. Lange and T. Zeugmann* |

| | | **A Decision-Tree Model of Balance Scale Development** - *William C. Schmidt and Charles X. Ling* |

| | | **Strong minimax lower bounds for learning** - *András Antos and Gábor Lugosi* |

| | | **A generalized reinforcement-learning model:convergence and applications** - *Michael L. Littman and Csaba Szepesvári* |

| | | **Toward optimal feature selection** - *Daphne Koller and Mehran Sahami* |

| | | **Learning active classifiers** - *Russell Greiner, Adam J. Grove and Dan Roth* |

| | | **Game theory, on-line prediction and boosting** - *Yoav Freund and Robert E. Schapire* |

| | | **Speeding-up nearest neighbour memories: the template tree case memory organisation** - *Stephan Grolimund and Jean-Gabriel Ganascia* |

| | | **On the learnability of the uncomputable** - *Richard H. Lathrop* |

| | | **Applying the multiple cause mixture model to text categorization** - *Mehran Sahami, Marti Hearst and Eric Saund* |

| | | **Theoretical analysis of the nearest neighbor classifier in noisy domains** - *Seishi Okamoto and Nobuhiro Yugami* |

| | | **K nearest neighbor classification on feature projections** - *s Aynur Akku\ and H. Altay Güvenir* |

| | | **Learning sparse multivariate polynomials over a field with queries and counterexamples** - *Robert E. Schapire and Linda M. Sellie* |

| | | **Challenges in machine learning for text classification** - *David D. Lewis* |

| | | **The characterisation of predictive accuracy and decision combination** - *Kai Ming Ting* |

| | | **Constructive induction using fragmentary knowledge** - *Steve Donoho and Larry Rendell* |

| | | **Robot Programming by Demonstration RPD : Supporting the Induction by Human Interaction** - *H. Friedrich, S. Münch, R. Dillman, S. Bocionek and M. Sassin* |

| | | **On the Worst-Case Analysis of Temporal-Difference Learning Algorithms** - *Robert E. Schapire and Manfred K. Warmuth* |

| | | **Toward a model of mind as a laissez-faire economy of idiots** - *Eric B. Baum* |

| | | **Error Reduction through Learning Multiple Descriptions** - *Kamal M. Ali and Michael J. Pazzani* |

| | | **Learning radial basis function networks on-line** - *E. Blanzieri and P. Katenkamp* |

| | | **Theory-guided induction of logic programs by inference of regular languages** - *Henrik Boström* |

| | | **On the complexity of learning from drifting distributions** - *Rakesh D. Barve and Philip M. Long* |

| | | **Technical Note: Some Properties of Splitting Criteria** - *Leo Breiman* |

| | | **Guest Editor’s Introduction by Thomas Hancock** - *Thomas Hancock* |

| | | **Bias plus variance decomposition for zero-one loss functions** - *Ron Kohavi and David H. Wolpert* |

| | | **PAC-like upper bounds for the sample complexity of leave-one-out cross-validation** - *Sean B. Holden* |

| | | **Lower bound on learning decision lists and trees** - *Thomas Hancock, Tao Jiang, Ming Li and John Tromp* |

| | | **The Effect of Representation and Knowledge on Goal-Directed Exploration with Reinforcement-Learning Algorithms** - *Sven Koenig and Reid G. Simmons* |

| | | **Sensitive discount optimality: unifying discounted and average reward reinforcement learning** - *Sridhar Mahadevan* |

| | | **Classification by feature partitioning** - *H. Altay Güvenir and Izzet Sirin* |

| | | **Using the Minimum Description Length Principle to Infer Reduced Ordered Decision Graphs** - *Arlindo L. Oliveira and Alberto Sangiovanni-Vincentelli* |

| | | **Set-driven and rearrangement-independent learning of recursive languages** - *S. Lange and T. Zeugmann* |

| | | **On-line portfolio selection using multiplicative updates** - *David P. Helmbold, Robert E. Schapire, Yoram Singer and Manfred K. Warmuth* |

| | | **On Bayes methods for on-line Boolean prediction** - *Nicolò Cesa-Bianchi, David P. Helmbold and Sandra Panizza* |

| | | **Learning relational concepts with decision trees** - *Peter Geibel and Fritz Wysotzki* |

| | | **Beyond independence: conditions for the optimality of the simple Bayesian classifier** - *Pedro Domingos and Michael Pazzani* |

| | | **Applying the weak learning framework to understand and improve C4.5** - *Tom Dietterich, Michael Kearns and Yishay Mansour* |

| | | **Representation of finite state automata in recurrent radial basis function networks** - *Paolo Frasconi, Marco Gori, Marco Maggini and Giovanni Soda* |

| | | **Discretizing continuous attributes while learning Bayesian neworks** - *Nir Friedman and Moises Goldszmidt* |

| | | **PAC learning intersections of halfspaces with membership queries** - *Stephen Kwek and Leonard Pitt* |

| | | **Causal discovery via MML** - *Chris Wallace, Kevin B. Korb and Honghua Dai* |

| | | **On restricted-focus-of-attention learnability of Boolean functions** - *Andreas Birkendorf, Eli Dichterman, Jeffrey Jackson, Norbert Klasner and Hans Ulrich Simon* |

| | | **A data dependent skeleton estimate for learning** - *Gábor Lugosi and Márta Pintér* |

| | | **Introduction** - *Leslie Pack Kaelbling* |

| | | **Exact classification with two-layer neural nets** - *Gavin J. Gibson* |

| | | **Residual Q-learning applied to visual attention** - *Cesar Bandera, Francisco J. Vico, Jose M. Bravo, Mance E. Harmon and Leemon C. Baird III* |

| | | **A competitive approach to game learning** - *Christopher D. Rosin and Richard K. Belew* |

| | | **Average Reward Reinforcement Learning: Foundations, Algorithms, and Empirical Results** - *Sridhar Mahadevan* |

| | | **Stacked Regressions** - *Leo Breiman* |

| | | **Creating Advice-Taking Reinforcement Learners** - *Richard Maclin and Jude W. Shavlik* |

| | | **On the Limits of Proper Learnability of Subclasses of DNF Formulas** - *Pillaipakkamnatt Krishnan and Raghavan Vijay* |

| | | **Learning in the Presence of Concept Drift and Hidden Contexts** - *Gerhard Widmer and Miroslav Kubat* |

| | | **Exponentially many local minima for single neurons** - *P. Auer, M. Herbster and M. K. Warmuth* |

| | | **Trees and learning** - *Wolfgang Merkle and Frank Stephan* |

| | | **An advanced evolution should not repeat its past errors** - *Caroline Ravis’e and Michèle Sebag* |

| | | **On-line portfolio selection** - *Erik Ordentlich and Thomas Cover* |

| | | **A randomized approximation of the MDL for stochastic models with hidden variables** - *Kenji Yamanishi* |

| | | **Worst-case Loss Bounds for Single Neurons** - *D. P. Helmbold, J. Kivinen and M. K. Warmuth* |

| | | **Learning conjunctions of two unate DNF formulas: computational and informational results** - *Aaron Feigelson and Lisa Hellerstein* |

| | | **On the structure of the Degrees of Inferability** - *Martin Kummer and Frank Stephan* |

| | | **Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning** - *Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida and Koh Hosoda* |

| | | **Attribute-efficient learning in query and mistake-bound models** - *Nader H. Bshouty and Lisa Hellerstein* |

| April | | **Probably Approximately Optimal Satisficing Strategies** - *Russell Greiner and Pekka Orponen* |

| July | | **PALO: A probabilistic hill-climbing algorithm** - *Russell Greiner* |