Search

An abstract of the article "Functional role of opponent, dopamine modulated D1/D2 plasticity in reinforcement learning" by Jenia Jitsev, Nobi Abraham, Abigail Morrison, and Marc Tittgemeyer is presented.

An abstract is presented of the research paper "Self-generated off-line memory reprocessing on different layers of a hierarchical recurrent neuronal network," by Jenia Jitsev, which was presented at the Twentieth Annual Computational Neuroscience Meeting held in Sweden in July 2011.

Introduction We here address the problem of integrating information about multiple objects and their positions on the visual scene. A primate visual system has little difficulty in rapidly achieving integration, given only a few objects. Unfortunately, computer vision still has great difficultly achieving comparable performance. It has been hypothesized that temporal binding or temporal separation could serve as a crucial mechanism to deal with information about objects and their positions in parallel to each other. Elaborating on this idea, we propose a neurally plausible mechanism for reaching local decision-making for "what" and "where" information to the global multi-object recognition. Mechanism The model we propose here is inspired by the binding-by-synchrony as well as the dynamic link architecture. The decision-making is done by so-called control (C) macrocolumn units, which are responsible not only for the synchronization or de-synchronization of selected feature macrocolumns, but also for signaling the position of the object in the scene. The feature macrocolumns are placed on two distinct domains. The input (I) domain contains the sensory data from the scene while the gallery (G) domain stores the reference objects to be recognized. Each macrocolumn consists of subunits called minicolumns, which are bound together by common afferents and lateral inhibition modulated by an autonomous oscillator of the integrate-and-fire (IF) type, being a further development of the previous modeling approach of a macrocolumn cortex. The binding-by-synchrony, establishing the related dynamic links, is achieved via similarity computation between the feature columns and the similarity-based modulation of a time constant and weight of the IF synaptic couplings, influenced by the C column subunits. Results Figure 1 demonstrates that the binding-by-synchrony in our system is achieved so rapidly within a few of hundred milliseconds. More precisely, the IF neural oscillators in the feature macrocolumns of I and G with the higher similarity become synchronized with zero-lag, showing asynchronous behavior between the IF oscillators of the feature macrocolumns with lower similarity. Transition of synchrony to asynchrony occurs by modulating a time constant and weight of the IF synaptic couplings, under the influence of subunit activities in the C. The zero-lag synchronization between the IF oscillators is the global object recognition, assigning each object the corresponding position in the scene, which is signaled by the activities in the C column units. [ABSTRACT FROM AUTHOR]

Our work deals with the self-organization of a memory structure that includes multiple hierarchical levels with massive recurrent communication within and between them. Such structure has to provide a representational basis for the relevant objects to be stored and recalled in a rapid and efficient way. Assuming that the object patterns consist of many spatially distributed local features, a problem of parts-based learning is posed. We speculate on the neural mechanisms governing the process of the structure formation and demonstrate their functionality on the task of human face recognition. The model we propose is based on two consecutive layers of distributed cortical modules, which in turn contain subunits receiving common afferents and bounded by common lateral inhibition (Figure 1). In the initial state, the connectivity between and within the layers is homogeneous, all types of synapses -- bottom-up, lateral and top-down -- being plastic. During the iterative learning, the lower layer of the system is exposed to the Gabor filter banks extracted from local points on the face images. Facing an unsupervised learning problem, the system is able to develop synaptic structure capturing local features and their relations on the lower level, as well as the global identity of the person at the higher level of processing, improving gradually its recognition performance with learning time. The structure formation relies on the activity-dependent bidirectional plasticity and the homeostatic regulation of unit's activity. While these occur on the slow time scale, the fast acting neural dynamics with strong competitive character ensures that only a small subset of units may update their synapses during a decision cycle spanned by oscillatory inhibition and excitation in the gamma range. This repetitive selection triggered by certain face images leads to amplification of the memory trace for the respective person. Acting together, homeostatic constraint and bidirectional plasticity work on reducing the overlap between different memory traces, segregating them in the memory structure. The ongoing modification of the memory's structure conditions the system for more and more coherent communication between the bottom-up and top-down signals. The binding of the local features via lateral and top-down connections into a global identity enhances the generalization capability of the memory, and renders the system to reliably recognize novel face images of different views not presented before. The proposed mechanisms of learning reveal thus basic principles behind the self-organization of successful subsystem coordination. [ABSTRACT FROM AUTHOR]