Volume: 03, February 2014, Pages: 675-679 International Journal of Computing Algorithm Integrated Intelligent Research (IIR) 675 To Analyze Stress in Education Using Bam Model J. Maria Roy Felix, J. Shirley Joe Rita Department of Mathematics, Loyola College, Chennai - 600 034 Email: shirleyjoe92@gmail.com ABSTRACT In this paper we find how stress makes an impact in imparting knowledge using Bidirectional associative memories. Since no statistical data to this effect can be collected, we using a linguistic questionnaire interviewed 50 persons, from the group of educationalists, NGOs, youth, teachers etc. and using these interviews constructed the FRM model, relating the effect of stress on the physical, mental and emotional balance while preparing the student to gain knowledge . We use BAM models to study, analyze this problem of stress management among the teachers to shape up our young minds in education. KEY WORDS: BAM, Stress, Education. SECTION ONE: 1.1. INTRODUCTION We have interviewed 50 persons from Chennai using linguistic questionnaire. Later this questionnaire was converted into Fuzzy data. Using expert’s opinion, we obtain the 7x8 synaptic connection matrices in the scale [5,-5] and denote it by M 1. This paper has four sections. i. We recall the definition and properties connected with Bidirectional Associative Memories (BAM) ii. Description of the problem. iii. We adapts BAM to this problem and analyze the problem iv. We drive conclusions and make some suggestions. 1.2 Bidirectional Associative Memories. (BAM) 1.2.1. Neuron Fields Group neurons form a field. Neural networks contain many fields of neurons. F x denotes a neuron field which contains n neurons and F y denotes a neuron field which contains p neurons. 1.2.2. Neuronal Dynamical Systems The neuronal dynamical system is described by a system of first order differential equations that govern the time evaluation of the neuronal activations or membrane potentials. Where x i and y j denote respectively the activation time function of the i th neuron in F x and the j th neuron in F y . The over dot denotes time differentiation, g i and h j are functions of X, Y etc., Where X(t) = (x 1 (t),……..,x n (t)) and Y(t) = ( y 1 (t),…….,y n (t)) Define the state of the neuronal dynamical system at time t. Additive bivalent Models describe asynchronous and stochastic behavior. At each moment each neuron can randomly decide whether to change state, or whether to omit a new signal given its current activation. The BAM is a non- adaptive, additive, bivalent neural network. 1.2.3. Bivalent Additive BAM In neural literature, the discrete version of the earlier equations are often referred to as the Bidirectional Associative Memories or BAM s. A discrete additive BAM with threshold signal functions, arbitrary thresholds and inputs, an arbitrary but a constant synaptic connection matrix M and discrete time steps K are defined by the equations. . i i . j j X g ( X, Y, .... ) Y h ( X, Y, .... )   p k+1 k i j j ij i j n k+1 k j i i ij j i ij i j 1 x S (y )m I y S (y )m I Where m M. S and S are the signal functions. they represent binary or pipolar thresho ld functions. For arbitrary real-valued thresholds U = ( U , ....        n x 1 p y ..........,U ) for F neurons and V = (V , ...........,V ) for F neurons,the threshold binary signal functions corresponds neurons