Feed Forward Neural Networks

Author: Marek Libra

A brief note prior reading: I suggest to read introduction to Artificial Neural Networks before reading that Knol.

---

The Feed Forward Neural Networks (FFNNs) represent a subclass of perceptron networks.Same as other perceptron networks, the FFNNs are computed with discrete time. The models using the discrete time are used for solving practical problems very often due to generally good theoretical understanding of those models and especially due to their ability to be easily simulated on von Neumann machines.

A feed-forward network is an acyclic graph of neurons unambiguously signed (weighted) by numbers from R (real numbers). The neurons are grouped into a sequence of d + 1 pair wise disjoint layers. The neurons are connected only to the neurons in a subsequent or previous layer.

The layers are called input, output and hidden in a feed-forward NN. The input and output layers must be present exactly once per each in a network. These layers build the network interface. The hidden layers are optional and there can be more than one.

The number of layers excluding the input one is called the depth and equals to the d. The connection (sometimes called synapse) between neuron i and j is evaluated by the weight w_ij . The w_ij = 0 means there is no connection from the i to the j neuron.

FFNNs are notated according to counts of neurons in their layers. For example the 3-1-2-4 FFNN notation points to an FFNN with 3 input neurons, 1 neuron in the first hidden layer, 2 neurons in the second hidden layer and 4 output neurons, as depicted on the following figure:

The computation of an FFNN is done gradually, layer by layer, where the outputs of one layer neurons serve as the inputs for the subsequent layer neurons.
Initially, the states (means outputs) of neurons in the input layer are set to represent the external input.
The states of neurons in a subsequent hidden or output layer are computed in parallel. The neuron computing its output takes the output of the preceding neurons as its input. The neuron j computes a weighted sum of the inputs called the inner potential ε _j ∈ R:

where the j← is a set of input neurons for neuron j (means from preceding layer) and y _i is the output of the neuron i.
The nonlinearity is introduced to an NN using an activation function σ computed on the inner potential ε:

σ : R −→ (0, 1).

The activation function must be differentiable on R or at least on a subset of R which is used by the neurons to solve a particular problem. The differentiability is necessary especially for the back-propagation algorithm.

The commonly used activation function is the standard sigmoid:

The λ is a parameter of this function used for optimization of the network’s behavior. The λ determines the function steepness and its value can differ for neurons in an NN in general.

The actual computation of σ is problem-specific, but the standard sigmoid on the interval (0, 1) is commonly used for computation of σ(ε).
Another also popular activation function seems to be the hyperbolic tangents, where σ = tangh:

A discussion about the activation function’s behavior can be found in [1] .

Further Reading

Knol

• Artificial Neural Networks
• Adaptation of Feed-Forward Neural Networks (contains farther links)
  
• My Knol Directory

External

• [1] David M Skapura. Building Neural Networks. Addison-Wesley, 1995.

Source Url: Feed Forward Neural Networks

Knol - 5195

Adaptation of Feed Forward Neural Networks

Author: Marek Libra

A brief note prior reading of this Knol: I suggest to read

• introduction to Artificial Neural Networks
  
• and Feed Forward Neural Networks

---

There are two main purposes for considering artificial NNs
    • the study of biological decision mechanisms (like human brain) and/or
    • the machine learning paradigm useful for implementing of decision logic in artificial agents or as a tool for statistical analysis as an alternative to classical approaches.

The main advantage of the NN paradigm compared to the deterministic Turing-like approaches are in absence of precise description for solving a particular problem like it is done in some general-purpose programming language (i.e. C++).

On the contrary, we consider the supervised learning where a pair of a training set and an FFNN architecture is used to describe the problem which is solved by the FFNN. The training set stays of pairs (given input, awaited output). These pairs are called patterns. The training set is provided by the FFNN user (human or machine).

For the completeness, the training set is not mandatory for computation with FFNNs. The adaptation function of an FFNN can be omitted (never used). Well specified weights for an FFNN are sufficient for proper computation of a network. Unfortunately, it is very difficult to properly set the weights by the NN designer.

For this reason, there are introduced multiple learning mechanisms which can adapt the weights automatically. Each the learning algorithm has different ability to provide generalization to the network.

The ability of network to solve a particular problem is measured by the network error on a set of patterns L of size p:

where the E_k is called the partial error of network on the pattern k:

where the Y is a set of output neurons (determined by the FFNN topology), the y _j (x_k ) is the computed output of the neuron j after network computation on the input vector x_k . The d_kj is the awaited output of the neuron j after network computation on the input x _k .

The learning algorithm adapts the weights to minimize the network error on a training set. However the training set is used for the error evaluation during the adaptation, the testing set is used to evaluate the efficiency of the network for solving the problem. More precisely, the testing set stays from patterns similarly as the training set. The testing set can be disjoint to the training set. This simple methodology shows better the network capability to handle an unknown input.

The goal of the adaptation process must not be necessarily in the zero network error on the training set but in a reasonable low error on the testing set. Moreover, a low value of a network error must not necessarily mean a good network for solving a problem. There is a big issue in the over training, when the network doesn’t generalize the given data but it just memorizes them. Such an over trained network lacks the ability to classify correctly the output on newly (not previously given) input. Some aspects of the over training issue are mentioned in [1].

Further Reading

Knols

• Artificial Neural Networks
• Feed-Forward Neural Networks
• The Perceptron Rule
• The Back Propagation
• My Knol Directory

External

• [1] S. Amari, N. Murata, K.-R. M ̈ ller, M. Finke, and H. H. Yang. Asymptotic statistical theory of overtraining and cross-validation. IEEE Transactions on Neural Networks, 8(5):985–996, September 1997.
  

Source Url:  http://knol.google.com/k/marek-libra/adaptation-of-feed-forward-neural/5rqq7q8930m0/15#

Knol Nrao - 5196

The Back Propagation - Algorithm

Author: Marek Libra

A brief note prior reading of this Knol: I suggest to read

• introduction to Artificial Neural Networks
  
• and Feed Forward Neural Networks
• and Adaptation of Feed-Forward Neural Networks
• and The Perceptron Rule
  

---

The Back Propagation (called BP later) is an algorithm used for adaptation of a multi-layered feed-forward neural network. It is based on the perceptron rule, but propagating the effect of the overall network error into inner parts of the network.

The network error computation on the training set is based on the complicated nonlinear function. It is a classical hard optimization problem to minimize the network error value and the BP tries to deal with it.

The BP uses gradient descent method which demands the differentiability of the network error function. Obviously, the differentiability of the network error function relies on the differentiability of the activation function (due to the feed-forward computation mechanism described in the preceeding Adaptation of Feed-Forward Neural Networks Knol).

The Knol you are reading aims for the standard sigmoid as the activation function in the description of the following equations. This function is commonly used in practical experiments.
                         
Initially, the weight w_ij⁰ from the neuron i to the neuron j is set randomly for each interconnected neurons i and j at the time t=0.
The adaptation is computed in a loop of discrete steps (begin at time t = 1, increment t in each subsequent step).

The weights w_t of time t ensue from the weights w_t−1 of time t−1 by incrementing a negative gradient of the network error at the point w_t−1 multiplied by a learning speed parameter e ∈ R:

Eq. 1

The parameter e is set accordingly in interval 0 < e < 1 by the user or by some supporting algorithm. Its value can be changed during the learning process to tune the adaptation behavior (learning speed or skipping over local extremes).

The gradient

in Eq. 1 is computed from

Eq. 4

The function of the network can be considered as a composite function of neurons. We can differentiate the gradient in previous equotation using the rule for a composite function:

Eq. 2

By usage of standard sigmoid and inner potential definition (described in Feed-Forward Neural Networks):

Eq. 3

Next, the back propagation strategy is used for computation of the partial derivation:

• for a neuron j in output layer:
  
• for a neuron j in hidden layer:
  

where j^→ is a set of neurons with j as its input.

Same as other gradient descent methods, the main disadvantage of the BP is in locating of a local
minimum. It is very difficult to reach the global minimum with such approaches. Some heuristics
based a stochastic extension of BP or on tuning of the learning speed parameter exist but they
are not optimal in general.

Following simplified BP algorithm is provided for better description. The ∆E is a matrix used for step-by-step computation
of the network error gradient.

The claim to discovery of the BP is controversial. Initially, it was accepted to have been discovered independently by Rumelhart, Hinton and Williams (1986), Le Cun (1985), and Parker (1985). But it was mainly the work by Rumelhart et. al. who made the model popular. He published his original article as [1].

Further Reading

Knols

• Artificial Neural Networks
• Feed-Forward Neural Networks
• Adaptation of Feed-Forward Neural Networks
• The Perceptron Rule
• My Knol Directory

External

• [1] D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Bradford Books/MIT Press, Cambridge, 1986.
  

Source Knol: The Back Propagation

Knol Narayana rao - 5198

Artificial Neural Networks - Interesting Web Pages

1. 15 Steps to implement a neural network

http://code-spot.co.za/2009/10/08/15-steps-to-implemented-a-neural-net/
Good explanation, simple mathematical functions and some code to use are given

Neural Networks - Introduction - Video Lecture

An interesting introductory lecture

http://www.youtube.com/watch?v=6ixqKw7uK6o

Nokia 500 Smart Phone

http://www.youtube.com/watch?v=24xPEo0FFlY&feature=topvideos_science

 

1 Gigahertz Processor

http://www.youtube.com/watch?v=-YJdCO-F9Bc&feature=related

Syllabus - Computer Science - Engineering - Mumbai University

First year to Fourth Year

Authors

• Narayana Rao

Published

Creative Commons Attribution 3.0 License

Version 10

Last edited: 22 Sep 2011

Exported: 26 Nov 2011

Original URL: http://knol.google.com/k/-/-/2utb2lsm2k7a/1644

Computer Science and Engineering Mumbai University Syllabus

Download the syllabus for all years from

http://www.terna.org/downloads.php

III semester
http://www.terna.org/syllabus/Comp/III.pdf

IV Semester
http://www.terna.org/syllabus/Comp/IV.pdf

V Semester
http://www.terna.org/syllabus/Comp/V-NEW.pdf

Vi Semester
http://www.terna.org/syllabus/Comp/VI-NEW.pdf

VII Semester
http://www.terna.org/syllabus/Comp/VII-NEW.pdf

VIII Semester
http://www.terna.org/syllabus/Comp/VIII-NEW.pdf

__________________________________________________________________________________

Sub-Directories of Knols in the Area of Computer Science and Engineering

Knol Sub-Directory - Computer Science, Engineering and Technology - Subjects
New link

Knol Sub-Directory - New Knols - Computer Science, Engineering and Technology

Computer Science, Engineering, and InformationTechnology - Mumbai University Syllabus - Knol Books and Notes
New link

Computer Science and Engineering - Knol Books - Catalogue New link

_______________________________________________________________________________________

SEMESTER I

1. APPLIED CHEMISTRY I

Water: Impurities in water and their effects on quality, hardness and estimation of hardness by soap and EDTA methods, problems
based on determination of hardness, softening of water, methods of softening: lime soda, permutit and ion exchange methods,
calculation of requirement of softening reagents, boiler feed water, boiler problems and methods of rectification, industrial uses of
water.

Refractories: Definition, criteria of good refractories, classification of refractories ,properties, testing and failure of refractories,
glass, manufacture and properties, types of glass.
Polymers: Classification of polymers, types of polymerization, methods of polymerization, classification of plastics, compounding of
plastics, fabrication of plastics, industrial uses of plastics, manufacture, properties and uses of polyethylene, polyvinyl chloride,
phenol formaldehyde and urea fomaldehyde.
Lubricants: Definition and function ,classification: solid, semisolid, blended and synthetic lubricants. purification and refining of
lubricants from mineral oils, mechanism of lubrication, physical and chemical testing of lubricants, testing of lubricants.
Elastomers: Natural rubber, its drawbacks, vulcanisation and its effects upon properties, compounding of rubber, synthetic rubber:
nitrile, neopropene, polyurethane, silicon and styrene rubber. Industrial uses of rubber and recovery of rubber from waste.
Pollution and Pollution Control: Atmospheric pollution, nature of pollutants, their effects and methods to reduce atmospheric
pollution. water pollution, nature of pollutants, their effects and methods to reduce water pollution.

2. APPLIED MATHEMATICS - I

Complex Variables: Definition, Cartesian, polar & amplitude ; exponential form. de moivres theorem. power & amp; roots of
exponential and trigonometric forms. hyperbolic and logarithmic functions. inverse hyperbolic and inverse trigonometric of all types
of functions.
Vector Algebra: Triple Product, Vector Differentiation, Curvature and Torsion, Equation of planes.
Calculus: Successive differentiation, std form to find the nth derivative, Leibnitz theorem, Rolles theorem ,Lagranges and Cauchys
mean value theorem, Taylors theorem, Taylor and Maclaurins series, indeterminate forms, Lhospitals rule, expansion of functions
in power series, partial derivatives of first and higher orders, total differentiation concept of commutative partial derivatives, Eulers
theorems of homogeneous functions, deduction from Eulers theorems ,errors, approximations, maxima and minima functions of two
variables.

3. APPLIED PHYSICS - I

Elements of Crystal Structure: Packing Factor, Diamond cubic and Barium Titanate structure, Miller indices, indices of crystal
directions, ligancy and critical radius ratio of ionic crystals, crystal imperfections, expression of equilibrium, number of point defects.
Formation of energy bands and classification of solids: Conductors, insulators, semi conductors, intrinsic p and n type,
semiconductor diode as a rectifier, npn and pnp transistors.
Ultrasonics: Piezoelectric and magnetostriction effect ,piezoelectric crystals, quartz and ceramics, ultrasonic transducers,
application: echo sounding, thickness measurement, cavitation and non-destructive testing, flaw detection.
Thermoelectric Effect: Law of intermediate temperatures and metals, neutral temperature and inversion temperature, peltier
effect, thermocouple as a temperature measuring device, semiconductor as a device to measure temperature.(thermistors)
Motion of Charged ParticLes in Electric and Magnetic Fields : Magnetic and Electrostatic Focusing, cathode ray tube ,cyclotron,
mass spectrograph.( Aston and Bain bridge ).

4. BASIC ELECTRICITY AND ELECTRONICS I

Fundamentals of electricity: Units, electric current, Ohms law, Kirchoffs laws, loop and nodal analysis, series and parallel
combination of resistances.
Network theorems: Star delta transformation, superposition theorem, Thevenins theorem,Nortons theorem, maximum power
transfer theorem.
Electromagnetism: Amperes law, force between magnetic poles, field intensity, flux, flux density, Biot- Savarts law, mmf,
reluctance, magnetisation curve, hysteresis loop and losses, series and parallel magnetic circuits, self and mutual inductance, laws
of electromagnetic induction, Flemings right and lefthand rule, energy stored in an inductor, rise and decay of current in r-l circuit,
time constant.
Electrostatics: Coulombs law, electric field, electric field intensity, electric flux and flux density, absolute electric field potential and
potential difference, dielectric and dielectric strength, capacitance, parallel plate capacitor, composite parallel plate capacitor,
energy stored, charging and discharging in r-c circuits, capacitances in series and parallel.

5. COMPUTER PROGRAMMING I

Basic Anatomy of Computers: Components of computer systems, IBM compatible PC
Introduction to operating systems: Need for an operating system, internal commands of MS- DOS, external commands. batch
files, introduction to system software.
Mumbai University Bachelor of Engineering COMPUTERS Revised Syllabus
19
Introduction to Lotus 1-2-3: Worksheet usi ng keyboard with 1-2-3 basic skills, using 1-2-3 menus, commands indicating range of
cells moving pointer, constructing blank forms, changing entries in the cell, sorting the worksheet, using formulae, keyboard
macros.
Pascal Programming:
·  Introduction to computer programming, steps involved in computer programming, the problem definition phase.
·  Algorithms ,developing algorithms, efficiency of algorithms
·  Simple Pascal-concept of data types, the standard scalar data types, additional scalar data types, names in Pascal, scalar
variables.
·  Elementary Pascal programming, arithmetic expressions, use of standard functions, boolean expressions, the assignment
statement, input and output, structure of a Pascal program.

6. COMMUNICATION SKILLS I

Communication: What is communication? Importance of communication, barriers to communication, verbal and non verbal
communication, oral and written communication ,techniques to improve communication, internal and external communication.
Business correspondence: Principles of correspondence, language style, format of the business letter, types of business letters,
application letter with bio data. enquiries, reply to enquiry, claims, adjustments, sales letters.
Group Discussion: Importance of group discussion, techniques of group discussion.
Precis Writing: Importance of precis, techniques of precis writing, one word substitution, precis of short units, precis of passages,
summaries of letter reports, short messages.

7. ENGINEERING DRAWING I
·  Introduction, Lettering
·  Engineering Curves
·  Parabola, Ellipse, Hyperbola, Cycloid, Epicycloid, Hypercycloid, Involutes, Archemedian spirals, tangents and normals to
the above curves, simple helical curves on cylinder and cones.
·  Projection of Points and Lines
·  Projections of planes including planes inclined to both planes.
·  Projections of solids prism, pyramids ,cylinder and concluding those axes inclined to both the HP and VP
·  Sections of Solids
·  Orthographic Projections.

8. ENGINEERING MECHANICS I

System of Coplanar Forces: Resultant of concurrent forces, parallel forces and non parallel non concurrent system of forces,
moment of force about any point, couples, Varignons theorem, distributed forces in plane.
Centroids of plane areas: Center of gravity of wires bent into different shapes, moment of inertia of plane areas.
Equilibrium of system of coplanar forces: Conditions of equilibrium for concurrent, parallel and non concurrent, non parallel
system of forces and couples. types of supports, determination of reactions at supports for various types of structures.
Analysis of pin jointed plane frames: Perfect frame ,method of joints, method of sections.
Forces in space: Resultant of concurrent, parallel ,general force system. moment of a force about a point, finding scalar and
vector components of the force and the moment of the force along the axis.
Equilibrium of forces in space: Condition of equilibrium ,application to simple space pin jointed frames having roller/hinged
supports by method of joints.
Friction: Laws of friction, cone of friction ,equilibrium of bodies on an inclined plane, application to problems involving wedges
,ladders, screw jack etc.
Virtual work: Equilibrium for an ideal system, applications to the reactions of beam with internal hinges and link systems.
Graphic statics: Bows notation, force polygon, funicular polygon, Maxwell diagram, problems involving beam reactions, centroid of
plane areas or bent bars, determination of forces in trusses.

SEMESTER II

1. APPLIED MATHEMATICS - II

Differential Equations:
1. Exact differential Equations and those which can be made exact by use of integrating factor. Integrating factor by inspection,
Linear equations & reducible to linear (Bernoulli equations), method of substitution to reduce the eqn. to one of the above forms.
2. Linear Diff. Eqn. of nth order with constant coefficients, complimentary function & particular integral when the function of the
integral on the R.H.S. are exponential, Sin(ax + b), Cos(ax + b).Cauchys Linear equation( Homogenous eqn.). The Legendre Linear
equation, Variation of parameters & method of undetermined coefficients.
3. Elementary application of above diff. Eqn. in solving engineering problems from Electrical Engg., Chemical Engg., Mechanical
Engg., and Civil Engg.
Integral Calculus: Rectification of plane curves, Double and Triple integrals, Their geometrical interpretation & evaluation.
Evaluation of double integrals by change of order and change to polar. Application of double and triple integrals to areas, volumes
& mass.
Beta & Gamma Functions:
1. Beta & Gamma function & their properties, relation between Beta & Gamma functions.
2. Error Functions.
3. Differentiation under the integral sign.

2. APPLIED PHYSICS II
Theory of production of X-rays: Continuous and Characteristic X-rays spectra, X-ray diffraction, Laue spots, Braggs law and
Moseleys law. Determination of crystal structure. Braggs spectrometer method and power method.
Optics: Interference in thin film, Newtons rings and fringes in wedge shaped films. Fraunhoffer diffraction grating ( with derivation
of formula ).
Mumbai University Bachelor of Engineering COMPUTERS Revised Syllabus
16
Principles of Laser: Spontaneous and Stimulated radiation, Population inversion, Pumping methods. Ruby and He -Ne laser,
Carbon dioxide laser, Semiconductor lasers ( Dye lasers and holography ).
Fiber Optics: Types of optical fibres, step index and graded index, numerical aperture. Communication through optical fibers.
Dual nature of matter: DeBroglie waves, Verification of matter waves, uncertainty principle, electron microscope- Introduction and
application. Detection and measurement of radiation. Structure of nuclear binding energy, Nuclear fission. Nuclear reactors,
Nuclear fusion. Detection and measurement of nuclear radiation by emulsion plates, cloud chamber & Bubble chamber.
Super Conductivity: Basic theory, Meissner effects, London equation, properties of super conductors.
3. APPLIED CHEMISTRY II
Phase rule: Basic principles of phase rule, application of phase rule to water system. Condensed phase rule, allotropes of iron,
study of iron-carbon equilibrium diagram.
Corrosion: Definition, electrochemical theory of corrosion, factors affecting the rate of corrosion, different types of corrosion,
protection against corrosion, factors affecting the rate of corrosion - design and selection. Cathodic and anodic protection,
protective coatings- metallic, inorganic, organic coatings, corrosion inhibitors.
Fuels: Classification, calorific value, determination by bomb calorimeter and Dulongs formulae, problems based on calorific value,
characteristics of fuel, types of coal and its analysis. Preparation and properties of metallurgical coke. Liquid fuels, classification,
refining of petroleum, thermal and catalytic cracking, synthetic gasoline, purification of gasoline, knocking, octane and cetane
number, anti knock agents. Gaseous fuels - natural gas, coal gas, producer gas, water gas. Problems based on combustion of
fuels.
Cement: Raw materials, composition, method of manufacture : wet and dry process. Properties of cement, setting and hardening
of cement, testing of cement.
Alloys: Introduction, purpose of making alloys, composition. Properties and uses of plain carbon steels and alloy steels - heat
resistant steel, shock resistant steels, magnetic steels, corrosion resistant steels, tool steels. Non Ferrous alloys - Copper(Brass,
Bronze, German Silver), Nickel(Nichrome, Monel), Aluminium (Duralumin, Y-alloy, Magnalium), Lead and Tin (Solders, Brazing
alloys, type metal, wood metal ).
Biotechnology: Introduction, application to waste treatment, energy development, industrial product development, basic ideas of
industrial fermentation.
4 ENGINEERING DRAWING II
·  Development of lateral surfaces of solids when cutting plane is perpendicular to H.P. or V.P. including curved cuts.
·  Intersection of surfaces of solids- prism, pyramid, cone or cylinder penetrated by any prism or cylinder.
·  Isometric & Oblique parallel projections, simple block and cylindrical type objects & spheres.
·  Primary auxiliary views of machine parts involving inclined surfaces.
·  Reading of orthographic projections, drawing of missing views & converting into sectional views.
·  Free hand sketches of the following machine elements
1. Rivet heads and riveted joints.
2. Thread profiles of IS V & square threads, metric, buttress, acme, knuckle, I.S. convention of representing
external and internal V and square threads.
3. Bolts- hexagonal, square-prevention of rotation of bolts.
4. Nuts-hexagonal, square, wingnut locking by lock nuts, castle nut, split pin lock plate.
5. Studs- plain- collar.
6. Washer-plain, chamfered & spring washer.
7. Set screws.
8. Foundation bolts-rag, eye.
5. ENGINEERING MECHANICS II
Kinematics of a particle: Velocity and acceleration in terms of rectangular co-ordinate system. Rectilinear motion, motion along
plane curved path., tangential & normal components of acceleration, acceleration-time, velocity-time graphs and their uses,
projectile motion, simple harmonic motion.
Kinematics of rigid bodies: Translation, pure rotation & plane motion of rigid bodies, link mechanism, instantaneous centre of
rotation for the velocity & velocity diagrams for bodies in plane motion, acceleration in plane motion, relative velocities.
Kinetics of particles and kinetics of rigid bodies: D'Alemberts principle, equation of dynamic equilibrium, linear motion,
curvilinear motion, mass moment of inertia about centroidal axis & about any other axis. D'Alemberts principle for bodies under the
motion of rotation about a fixed axis and plane motion. Application to motion of bars, cylinders, spheres.
Momentum and Energy principles: Linear momentum, principle of conservation of momentum, work done by a force. Workenergy
equation, principle of conservation of energy, potential and kinetic energy & power, impact of solid bodies, elastic impact,
semi elastic and plastic impact.
Mumbai University Bachelor of Engineering COMPUTERS Revised Syllabus
17
Simple Lifting Machines: Mechanical Advantage, Velocity Ratio & efficiency of the machine, law of machine, condition of
maximum efficiency, self locking of the machine. Following machines will be studied- a) Single purchase crab, b) Double purchase
crab, c) Differential wheel and axle, d) Differential pulley block, e) worm and worm wheel, f) Simple screw jack.
Stress & Strain: Stress, Strain, modulus of elasticity, Bulk modulus, yield stress, ultimate stress, factor of safety, shear stress,
Poissons ratio, Bars of varying section, composite sections, temperature stresses.
Belt Friction: Transmission of power by belts and ropes, centrifugal and initial tension in the belts or ropes. Condition for maximum
power transmission. Flat belts on flat pulleys & ropes on grooved pulleys.
6. COMMUNICATION SKILLS II
Report Writing: . What is a report, qualities of a report, formats (letter report, memorandum, book report)
Reports. Informative report, analytical report, feasibility report, survey report, current event report.
Project. Practical session, topics to be assigned to group of students for report writing and presentation in class.
Meeting Documentation. Writing of a notice, agenda and minutes of a meeting.
Special types of exposition:
a) Description of objects.
b) Explanation of a process.
c) Giving instructions- oral instructions, written instructions.
7. COMPUTER PROGRAMMING II
·  Flow of control in Pascal, the compound statement, the iterative statement, conditional statements, unconditional
branching, avoidance of unconditional branching.
·  Structured Data types, Arrays and multidimensional arrays, Packed arrays, records and sets.
·  Functions and Subprograms, parameter passing.
·  Debugging and testing, documentation and maintenance.
·  Problem design methods, Top-down modular programming.
·  Additional Data structures, pointers, linked lists, list representations, node, operations on a linked list, binary search trees,
searching the tree, operations on a tree.
8. BASIC ELECTRICITY AND ELECTRONICS II
AC Circuits: Sinusoidal voltage and current, waveforms, RMS and average value, form factor, crest factor, frequency, periodic
time, behavior of resistance, inductance and capacitance in AC circuit, RLC series and parallel circuit, phasor diagram, resonance,
bandwidth and quality factor.
Polyphase Circuits: Three phase system of voltages and currents, star and delta connection, balanced three phase circuit,
relationship between line and phase currents and voltages, phasor diagram, power in three phase circuits, measurement of power
by one wattmeter, two wattmeter and three wattmeter methods.
Transformers: Construction of single phase transformers, function and working principle, development of equivalent circuit, phasor
diagram, O.C. and S.C. tests, efficiency and regulation, all day efficiency, condition for maximum efficiency.
Semiconductor Electronics: PN diode construction, characteristics, effect of temperature on diode, rectification using diodes, C,
L, LC and PI filters. BJT construction, characteristics, CE, CB and CC configuration.
9. BASIC WORKSHOP PRACTICE – (For semester I and semester II)
Fitting: Use of setting and fitting tools for chipping, cutting, filling, marking, Center punching, drilling , tapping, die threading.
Carpentry: Use and setting of hand tools like hacksaws, jack planes, chisels and gauges for construction of various joints, wood
turning, modern wood working methods, joining methods.
Welding: Use of welding machine. electric arc welding, edge preparation for welding, types of joints, Sheet metal working and
brazing: use of sheet metal working hand tools, cutting, bending, spot welding and brazing.
Forging and Smithy: Use and setting of hand tools such as hammers, chisels, flat and swages, use of hearth, anvil etc.
Machine tools and machining processes: Lathes, milling machines, drilling machines, grinding machines, operations such as turning,
milling, grinding and drilling.

Comments

Short urls

http://knol.google.com/k/-/-/2utb2lsm2k7a/1644
Narayana Rao - 22 Sep 2011