Akihiro Nakashima Eguchi

Akihiro Nakashima Eguchi
Microsoft

PhD computational neuroscience; BS computer science; BA Psychology

About

18
Publications
4,290
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
91
Citations
Education
October 2012
University of Oxford
Field of study
  • Computational Neuroscience
March 2008 - December 2011
University of Arkansas
Field of study
  • Computer Science

Publications

Publications (18)
Article
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Chapter
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...
Article
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Chapter
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Conference Paper
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Conference Paper
Full-text available
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...
Conference Paper
Full-text available
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...
Conference Paper
Full-text available
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...
Article
Full-text available
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’...

Network

Cited By

Projects

Projects (3)
Project
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 surrounding us to make our life better. Our project is goal-oriented, and the scope of this project is broad, encompassing Ubiquitous Intelligence, Cyber-Individual, Brain Informatics, and Web Intelligence. In this paper, we discuss how those technologies can be integrated together and fit into a seamless cycle like the one proposed in the Wisdom Web of Things (W2T). We also provide two case studies from our EiA project. The first case study is to demonstrate how a concept first tested in a virtual environment can be successfully implemented in the real world later when technological advances finally caught up. The data collection step and the ability to manually control smart objects of the W2T cycle are fulfilled in this step. The second case study is to show how the software simulator and hardware implementation are abstracted from the underlying algorithm, and thus, it serves as an example of how virtual worlds can be used as a test bed for W2T, especially with regards to the development of the remaining steps of the W2T cycle.
Project
The project focuses on a computational modeling investigation of the visually guided development of feature binding representations in the context of polychronization within a spiking neural network model. (Spike! v1.0 https://github.com/OFTNAI/Spike)