Consider the problem of learning input/output mappings through exploration, e.g.

It is well known that a given cortical neuron can respond with a different firing pattern forthe same synaptic input, depending on its firing history and on the effects of modulator transmitters (see [Connors and Gutnick, 1990] for a review). The time span of different channel conductances is very broad, and the influence of some ionic currents varies with the history of the membrane potential [Lytton, 1991]. Motivated bythe history-dependent nature of neuronal firing, we continue .our

Researchers often try to understand-post hoc-representations that emerge in the hidden layers of a neural net following training. Interpretation is difficult because these representations are typically highly distributed and continuous. By "continuous," wemean that if one constructed a scatterplot over the hidden unit activity space of patterns obtained in response to various inputs, examination at any scale would reveal the patterns to be broadly distributed over the space.

Many events such as flight delays or the absence of a member require the crew pool rescheduling team to change the initial schedule (rescheduling). In this paper, we show that the neural network comparison paradigm applied to the backgammon game by Tesauro (Tesauro and Sejnowski, 1989)can also be applied to the rescheduling problem of an aircrew pool. Indeed both problems correspond to choosing the best solut.ion

Transition point dynamic programming (TPDP) is a memorybased, reinforcementlearning, direct dynamic programming approach toadaptive optimal control that can reduce the learning time and memory usage required for the control of continuous stochastic dynamic systems. TPDP does so by determining an ideal set of transition points (TPs) which specify only the control action changes necessary for optimal control. TPDP converges to an ideal TP set by using a variation of Q-Iearning to assess the merits ofadding, swapping and removing TPs from states throughout the state space. When applied to a race track problem, TPDP learned the optimal control policy much sooner than conventional Q-Iearning, and was able to do so using less memory. 1 INTRODUCTION Dynamic programming (DP) approaches can be utilized to determine optimal control policiesfor continuous stochastic dynamic systems when the state spaces of those systems have been quantized with a resolution suitable for control (Barto et al., 1991). DP controllers, in lheir simplest form, are memory-based controllers that operate by repeatedly updating cost values associated with every state in the discretized state space (Barto et al., 1991).

We prove that the so called "loading problem" for (recurrent) neural networks isunsolvable. This extends several results which already demonstrated thattraining and related design problems for neural networks are (at least) NPcomplete. Our result also implies that it is impossible to find or to formulate a universal training algorithm, which for any neural networkarchitecture could determine a correct set of weights. For the simple proof of this, we will just show that the loading problem is equivalent to "Hilbert's tenth problem" which is known to be unsolvable.

The satisfiability of random CNF formulae with precisely k variables perclause ("k-SAT") is a popular testbed for the performance of search algorithms. Formulae have M clauses from N variables, randomly negated, keeping the ratio a M / N fixed .

We propose a computational model for how the cortex discriminates shape and depth from texture. The model consists of four stages: (1) extraction of local spatial frequency, (2) frequency characterization, (3) detection of texture compression by normalization, and (4) integration of the normalized frequency over space. The model accounts for a number of psychophysical observations including experiments based on novel random textures. These textures are generated from white noise and manipulated in Fourier domain in order to produce specific frequency spectra. Simulations with a range of stimuli, including real images, show qualitative and quantitative agreement with human perception. 1 INTRODUCTION There are several physical cues to shape and depth which arise from changes in projection as a surface curves away from view, or recedes in perspective.

Padhraic Smyth Jet Propulsion Laboratory 238-420 California Institute of Technology 4800 Oak Grove Drive Pasadena, CA 91109 Abstract This paper describes probabilistic methods for novelty detection when using pattern recognition methods for fault monitoring of dynamic systems. The problem of novelty detection is particularly acutewhen prior knowledge and training data only allow one to construct an incomplete classification model. Allowance must be made in model design so that the classifier will be robust to data generated by classes not included in the training phase. For diagnosis applications one practical approach is to construct both an input density model and a discriminative class model. Using Bayes' rule and prior estimates of the relative likelihood of data of known and unknown origin the resulting classification equations are straightforward.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexityissues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.