Exploiting Natural Asynchrony and Local Knowledge within Systemic Computation to Enable Generic Neural Structures

نویسندگان

  • Erwan Le Martelot
  • Peter J. Bentley
  • Beau Lotto
چکیده

Bio-inspired processes are involved more and more in today’s technologies, yet their modelling and implementation tend to be taken away from their original concept because of the limitations of the classical computation paradigm. To address this, [1] introduced systemic computation (SC), a model of interacting systems with natural characteristics, and [2] introduced a modelling platform with a bio-inspired system implementation. In this paper, we investigate the impact of local knowledge and asynchronous computation: significant natural properties of biological neural networks (NN) and naturally handled by SC. We present here a bio-inspired model of artificial NN, focussing on agent interactions, and show that exploiting these built-in properties, which come for free, enables neural structure flexibility without reducing performance.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Introduction of Local Knowledge on Watershed Management and Aquaculture in Iran (Case Study of Hormozgan Province)

Abstract Indigenous knowledge in the field of water and soil has attracted great attention due to its desirable functions, in particular ensuring high compatibility and maintaining ecological balance as well as attracting popular support and encouraging participation. The need for technology and knowledge that, while responding to the growing needs of societies, will also use the natural reso...

متن کامل

Exploiting Local Structures with the Kronecker Layer in Convolutional Networks

In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks. We use Kronecker product to exploit the local structures within convolution and fully-connected layers, by replacing the large weight matrices by combinations of multiple Kronecker products of smaller matrices. Just as the Kronecker product is a generalizatio...

متن کامل

Knowledge Extraction from the Neural ‘Black Box’ in Ecological Monitoring

Phytoplankton biomass within the Saginaw Bay ecosystem (Lake Huron, Michigan, USA) was characterized as a function of select physical/chemical indicators. The complexity and variability of ecological systems typically make it difficult to model the influences of anthropogenic stressors and/or natural disturbances. Here, Artificial Neural Networks (ANNs) were developed to model chlorophyll a con...

متن کامل

Ideational Grammatical Metaphor in Merry Shelly’s Frankenstein and its Cinematic Adaptation

Within Systemic Functional Linguistics, Grammatical Metaphor (GM) is a meaning-making resource lying at the experiential level that extends the meaning potential through cross-stratal re-mappings between the grammar and the semantics, boiling down, in one of its manifestations to expressing something that should have been a process (verb) in terms of a thing (noun). This study is an attempt at ...

متن کامل

First principles studies on band structures and density of states of graphite surface oxides

Graphite oxide constitutes carbon network with oxygen atoms both on hexagonal arrangement and the edge sites. Structural and electronic properties for graphite-oxygen complexes have been explored using first-principles total-energy calculations within the local density approximation (LDA). Band structures and density of states for the propose carbon 3D models are reported. A finite energy gap and...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007