Figure l(Dl-Gl)* depict some of the main STDP findings/ of which the best-investigated are shown in figure l(Dl;El), and are variants of based a'standard' STDP rule. Earlier work considered rate-based rather than spike temporal rules, and so we adopt the broader term'time dependent plasticity' or TDP. Note the strong temporal asymmetry in both the standard rules. Although the theoretical studies have provided us with excellent tools for modeling the detailed consequences of different time-dependent rules, and understanding characteristics such as long-run stability and the relationship with non-temporal learning rules such as BCM,6 specifically computational ideas about TDP are rather thinner on the ground. Two main qualitative notions explored in various of the works cited above are that the temporal asymmetries in TDP rules are associated with causality or prediction. However, looking specifically at the standard STDP rules, models interested in prediction *We refer to graphs in this figure by row and column.

The connectivity of the nervous system of the nematode Caenorhabditis elegans has been described completely, but the analysis of the neuronal basis of behavior in this system is just beginning. Here, we used an optimization algorithm to search for patterns of connectivity sufficient to compute the sensorimotor transformation underlying C. elegans chemotaxis, a simple form of spatial orientation behavior in which turning probability is modulated by the rate of change of chemical concentration. Optimization produced differentiator networks with inhibitory feedback among all neurons. Further analysis showed that feedback regulates the latency between sensory input and behavior. Common patterns of connectivity between the model and biological networks suggest new functions for previously identified connections in the C. elegans nervous system.

A common way of image denoising is to project a noisy image to the subspace of admissible images made for instance by PCA. However, a major drawback of this method is that all pixels are updated by the projection, even when only a few pixels are corrupted by noise or occlusion.

When we model a higher order functions, such as learning and memory, we face a difficulty of comparing neural activities with hidden variables that depend on the history of sensory and motor signals and the dynamics of the network. Here, we propose novel method for estimating hidden variables of a learning agent, such as connection weights from sequences of observable variables. Bayesian estimation is a method to estimate the posterior probability of hidden variables from observable data sequence using a dynamic model of hidden and observable variables. In this paper, we apply particle filter for estimating internal parameters and metaparameters of a reinforcement learning model. We verified the effectiveness of the method using both artificial data and real animal behavioral data.

Gradient-following learning methods can encounter problems of implementation in many applications, and stochastic variants are frequently used to overcome these difficulties. We derive quantitative learning curves for three online training methods used with a linear perceptron: direct gradient descent, node perturbation, and weight perturbation. The maximum learning rate for the stochastic methods scales inversely with the first power of the dimensionality of the noise injected into the system; with sufficiently small learning rate, all three methods give identical learning curves. These results suggest guidelines for when these stochastic methods will be limited in their utility, and considerations for architectures in which they will be effective.

We consider the problem of reconstructing patterns from a feature map. Learning algorithms using kernels to operate in a reproducing kernel Hilbert space (RKHS) express their solutions in terms of input points mapped into the RKHS. We introduce a technique based on kernel principal component analysis and regression to reconstruct corresponding patterns in the input space (aka pre-images) and review its performance in several applications requiring the construction of pre-images. The introduced technique avoids difficult and/or unstable numerical optimization, is easy to implement and, unlike previous methods, permits the computation of pre-images in discrete input spaces.

We propose an approach to learning the semantics of images which allows us to automatically annotate an image with keywords and to retrieve images based on text queries. We do this using a formalism that models the generation of annotated images. We assume that every image is divided into regions, each described by a continuous-valued feature vector. Given a training set of images with annotations, we compute a joint probabilistic model of image features and words which allow us to predict the probability of generating a word given the image regions. This may be used to automatically annotate and retrieve images given a word as a query. Experiments show that our model significantly outperforms the best of the previously reported results on the tasks of automatic image annotation and retrieval.

We describe a neuromorphic chip that utilizes transistor heterogeneity, introduced by the fabrication process, to generate orientation maps similar to those imaged in vivo. Our model consists of a recurrent network of excitatory and inhibitory cells in parallel with a push-pull stage. Similar to a previous model the recurrent network displays hotspots of activity that give rise to visual feature maps. Unlike previous work, however, the map for orientation does not depend on the sign of contrast.

Even under perfect fixation the human eye is under steady motion (tremor, microsaccades, slow drift). The "dynamic" theory of vision [1, 2] states that eye-movements can improve hyperacuity. According to this theory, eye movements are thought to create variable spatial excitation patterns on the photoreceptor grid, which will allow for better spatiotemporal summation at later stages.

We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. This paper addresses the issues of learning structured knowledge from a large-scale natural language data set, and of generalization to unseen text. The implemented algorithm represents sentences as paths on a graph whose vertices are words (or parts of words). Significant patterns, determined by recursive context-sensitive statistical inference, form new vertices. Linguistic constructions are represented by trees composed of significant patterns and their associated equivalence classes. An input module allows the algorithm to be subjected to a standard test of English as a Second Language (ESL) proficiency. The results are encouraging: the model attains a level of performance considered to be "intermediate" for 9th-grade students, despite having been trained on a corpus (CHILDES) containing transcribed speech of parents directed to small children.