Akihiro Nakashima Eguchi

Microsoft

We present a hierarchical neural network model, in which subpopulations of neurons develop fixed and regularly repeating temporal chains of spikes (polychronization), which respond specifically to randomised Poisson spike trains representing the input training images. The performance is improved by including top-down and lateral synaptic connection...

Experimental studies have shown that neurons at an intermediate stage of the primate ventral visual pathway, occipital face area, encode individual facial parts such as eyes and nose while neurons in the later stages, middle face patches, are selective to the full face by encoding the spatial relations between facial features. We have performed a c...

Objective: Cognitive bias modification (CBM) eliminates cognitive biases toward negative information and is efficacious in reducing depression recurrence, but the mechanisms behind the bias elimination are not fully understood. The present study investigated, through computer simulation of neural network models, the neural dynamics underlying the...

Neurons in successive stages of the primate ventral visual pathway encode the spatial structure of visual objects. In this paper, we investigate through computer simulation how these cell firing properties may develop through unsupervised visually-guided learning. Individual neurons in the model are shown to exploit statistical regularity and tempo...

Computers are getting smaller, cheaper, faster, with lower power requirements, more memory capacity, better connectivity, and are increasingly distributed. Accordingly, smartphones became more of a commodity worldwide, and the use of smartphones as a platform for ubiquitous computing is promising. Nevertheless, we still lack much of the architectur...

Modality-invariant categorical representations, i.e., shared representation, is thought to play a key role in learning to categorize multi-modal information. We have investigated how a bimodal autoencoder can form a shared representation in an unsupervised manner with multi-modal data. We explored whether altering the depth of the network and mixin...

We discuss a recently proposed approach to solve the classic feature-binding problem in primate vision that uses neural dynamics known to be present within the visual cortex. Broadly, the feature-binding problem in the visual context concerns not only how a hierarchy of features such as edges and objects within a scene are represented, but also the...

We use an established neural network model of the primate visual system to show how neurons might learn to encode the gender of faces. The model consists of a hierarchy of 4 competitive neuronal layers with associatively modifiable feedforward synaptic connections between successive layers. During training, the network was presented with many reali...

Color is an important part of our visual experience. The swirls of blues, yellows, and greens in Van Gogh's Starry Night affect a viewer in a way that a black-and-white rendition cannot. Color vision allows us to find a green bell pepper among red ones and predict how good it will taste. This article describes briefly the aspects of light that are...

As Rubin’s famous vase demonstrates, our visual perception tends to assign luminance contrast borders to one or other of the adjacent image regions. Experimental evidence for the neuronal coding of such border-ownership in the primate visual system has been reported in neurophysiology. We have investigated exactly how such neural circuits may devel...

In order to develop transformation invariant representations of objects, the visual system must make use of constraints placed upon object transformation by the environment. For example, objects transform continuously from one point to another in both space and time. These two constraints have been exploited separately in order to develop translati...

Experimental studies have shown that neurons at an intermediate stage of the primate ventral visual pathway encode the conformation and spatial relations of facial features [1], while neurons in the later stages are selective to the full face [2]. In this study, we investigate how these cell firing properties may develop through visually-guided lea...

Although many computational models have been proposed to explain orientation maps in primary visual cortex (V1), it is not yet known how similar clusters of color-selective neurons in macaque V1/V2 are connected and develop. In this work, we address the problem of understanding the cortical processing of color information with a possible mechanism...

The Everything is Alive (EiA) project at University of Arkansas is focused on pervasive computing. We consider that every physical object can be a living smart object and any services can be a living phenomenon. The goal of EiA is to make everything alive to make our lives revive with the objective to make use of all objects and services surroundin...

Simulation can be used to reduce the time and cost to develop a new technology. This paper describes the development of an autonomous floor mapping robot. In order to reduce the cost of building prototypes to test the program, we used the Simbad 3D simulator. To test in a more realistic environment, we established a way to control objects in a virt...

Minority game is a simulation of a zero-sum game, which has a similar structure to that of a real world market like a currency exchange market. We discuss a way to implement the game and provide a simulation environment with agents that can use various types of strategies to make decisions including genetic algorithms, statistics, and cooperative s...

The coming Internet of Things will usher in a semantic world (analogous to the semantic web) where physical objects will be networked so that they can communicate with each other and with humans. This paper identifies protocols that smart objects will need to follow and how to use today’s 3D virtual worlds to better design and understand those prot...

The coming Internet of Things will usher in a smart semantic world where many more physical objects will be networked so that they can communicate with each other and with humans. This paper identifies protocols that smart objects will need to follow and how to use today’s virtual worlds to better design and understand those protocols for tomorrow’...