The Neural Executive: Can Gated Attractor Networks Account for Cognitive Control?

نویسندگان

  • Jared Sylvester
  • James A. Reggia
چکیده

AI systems can be grouped into two main categories: symbolic and neural. Each has advantages in certain types of tasks, and to date symbolic systems are typically superior at cognitive control and executive function. This paper presents a model using the GALIS framework which probes at this gap by successfully completing the n-Back cognitive control task at human-like levels using a neural approach. Several aspects of the model discussed here, in particular gated sequential attractor networks and behavior driven in part from the learned contents of instruction memory, allow it to behave in ways that are more typical of symbolic systems.

برای دانلود رایگان 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

Neurocomputational Methods for Autonomous Cognitive Control

Title of Dissertation: NEUROCOMPUTATIONAL METHODS FOR AUTONOMOUS COGNITIVE CONTROL Jared Sylvester, Doctor of Philosophy, 2014 Dissertation directed by: James Reggia, Department of Computer Science Artificial Intelligence can be divided between symbolic and sub-symbolic methods, with neural networks making up a majority of the latter. Symbolic systems have the advantage when capabilities such a...

متن کامل

Attractor Networks

Artificial neural networks (ANNs), sometimes referred to as connectionist networks, are computational models based loosely on the neural architecture of the brain. Over the past twenty years, ANNs have proven to be a fruitful framework for modeling many aspects of cognition, including perception, attention, learning and memory, language, and executive control. A particular type of ANN, called a...

متن کامل

Neuropsychological and Neuropsychiatric Deficits Following Traumatic Brain Injury: Common Patterns and Neuropathological Mechanisms

Traumatic Brain Injury (TBI) in all degrees of injury severity mainly induces deviant cognitive, emotional and behavioral alterations that lead to their respective disorders. This brief overview strives to define the variables that determine the risk of occurrence of these disorders and to describe the common patterns of these disorders and their relevant neuropathogenetic mechanism(s). In addi...

متن کامل

Evaluating Cognitive Performance of Executive Control Based on Evidence from Attention Network Test and Event-Related Potential in Individuals with Mild Depressive Disorder and Burnout

Introduction: One of the secondary consequences of burnout is a significant reduction in cognitive functions, the most obvious and important of which is the cognitive function of attention and control, which can play a vital role in efficiency and prevention of errors at work in many occupations. On the other hand, a neurological examination is needed to understand better the relationship betwe...

متن کامل

Application of ANN Technique for Interconnected Power System Load Frequency Control (RESEARCH NOTE)

This paper describes an application of Artificial Neural Networks (ANN) to Load Frequency Control (LFC) of nonlinear power systems. Power systems, such as other industrial processes, have parametric uncertainties that for controller design had to take the uncertainties in to account. For this reason, in the design of LFC controller the idea of robust control theories are being used. To improve ...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013