Learning Fast and Slow

نویسندگان

  • John E. Laird
  • Shiwali Mohan
چکیده

We propose two distinct levels of learning for general autonomous intelligent agents. Level 1 consists of fixed architectural learning mechanisms that are innate and automatic. Level 2 consists of deliberate learning strategies that are controlled by the agent’s knowledge. We describe these levels and provide an example of their use in a task-learning agent. We also explore other potential levels and discuss the implications of this view of learning for the design of autonomous agents.

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

An Improved Particle Swarm Optimizer Based on a Novel Class of Fast and Efficient Learning Factors Strategies

The particle swarm optimizer (PSO) is a population-based metaheuristic optimization method that can be applied to a wide range of problems but it has the drawbacks like it easily falls into local optima and suffers from slow convergence in the later stages. In order to solve these problems, improved PSO (IPSO) variants, have been proposed. To bring about a balance between the exploration and ex...

متن کامل

Role of slow pathway after nodal fast pathway ablation on the basic and rate- dependent properties of the isolated rabbit atrioventricularNode

  Introduction : The aim of this study is to obtain new insight into possible relation between functional properties of slow concealed pathway and rate-dependent properties of AV-node.   Methods : Rate-dependent nodal properties of recovery, facilitation, and fatigue were characterized by stimulation protocols in one groups of (N=7) isolated superfused AV-Nodal rabbits. Small miniature lesions ...

متن کامل

Effect of progressive resistance exercise on β1 integrin and vinculin protein levels in slow-and fast-twitch skeletal muscles of male rats

Introduction: Skeletal muscle is a flexible and ever changing tissue and the role of costameric proteins in its response to different stimuli is not well defined. The aim of this study was to investigate the effect of progressive resistance exercise on β1 integrin and vinculin proteins in fast and slow twitch skeletal muscles of male rats. Methods: Twelve male Wistar rats (weight: 298±5.2 gr...

متن کامل

Effects of tripolar TENS of vertebral column on slow and fast motor units: A preliminary study using H-reflex recovery curve method

Introduction: Effect of tripolar TENS of vertebral column on slow and fast motoneurons (MNs) activity of soleus muscle was previously investigated. In this study for better differentiation of the behavior of slow and fast MNs, we exploited H-reflex recovery curve recording in two muscles of soleus and lateral gastrocnemius, respectively as the representatives of slow and fast muscles. Meth...

متن کامل

The Effect of Intensive Endurance Activity on Myocyte Enhancer Factor 2C Gene Expression of Slow and Fast Twitch Muscles in Male Wistar Rats: An Experimental Study

Background and Objectives: Myocyte enhancer factor 2c activates the genes of the slow-twitch muscle, the muscle which plays role in endurance activity. Therefore, the aim of this study was to evaluate the effect of a program of intensive endurance activity on MEF2c gene expression in fast and slow twitch skeletal muscles in wistar rats. Materials and Methods: In this experimental study, 14 mal...

متن کامل

بررسی کیندلینگ الکتریکی به وسیله تحریکات الکتریکی مکرر کف پای موش صحرایی

Background and purpose: Kindling is an animal model of epilepsy induced by repeated stimulation of the brain. The amygdala has been the focus of interest due to large part to its role in epilepsy induction and in fear conditioning in both human and rats. The purpose of the present study was to evaluate whether low electrical stimulation of foot pad of rats during fear can facilitate amygdala...

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 2017