The Department of COMPUTER SCIENCE AND APPLICATIONS conducted a one week STTP  on 02-11-2020 to 6-11-2020 titled DEEP LEARNING AND ITS APPLICATIONS HANDS-ON SESSION for teaching fraternity /for school students/for students. The Resource person Mr.RAMAR BOSE (Ph.D.,) (MCA 2012 – 2015 Batch)-Research Scholar, Anna University, Technical Advisor, Bodhashow-R&D Head, Research AIpro  spoke on


TOPIC: Introduction to deep learning Fundamentals of Artificial Neural Networks, Key aspects of Pattern Recognition.

? He then discussed about-

?What is neural network ?

?How a single neuron works?

?Why multi layer Networks are useful?

?General structure of a neural network?

?He explained about MIT Technology Review about AI/ML

?He explained about Deep learning , which is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.


Topic: Deep learning libraries, regression models with Keras, Deep neural networks: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Auto encoders (Hands-on sessions on CNN, RNN and Auto Encoders).

? Then he started about explaining  gradient descent algorithm- Gradient descent is a first-order iterative optimization algorithm for finding a local minimum of a differentiable function. To find a local minimum of a function using gradient descent, we take steps proportional to the negative of the gradient of the function at the current point

? He then discussed about-

?Implementing  Gradient descent  Algorithm with  Jupyter

?How to handle visualization


Introduction to Computer Vision in Machines and Image Acquisition, Lighting, Camera, and Optics, Machine Vision Solution Strategies, Acquiring and Displaying Images, Getting Measurement-Ready Images.

? He  discussed about-  A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. … Derived from feedforward neural networks, RNNs can use their internal state (memory) to process variable length sequences of inputs

?Training in RNN


Particle Analysis approach, Machine Vision Functions, Calibration for 2-D, Machine Vision Inspections, Considerations for Creating a Successful Vision Solution.

? Particle size analysis is a standard method in many quality control and research labs. The most common methods to determine the particle size are dynamic digital image analysis (DIA), static laser light scattering (SLS, also called laser diffraction) and sieve analysis.

? He then discussed about-  Machine vision uses sensors (cameras), processing hardware and software algorithms to automate complex or mundane visual inspection tasks and precisely guide handling equipment during product assembly. Applications include Positioning, Identification, Verification, Measurement, and Flaw Detection

The session/online session was attended by around 100 participants. The presentation was followed by a Q & A session. The webinar/workshop/event was well-coordinated by the faculty members Mr.N.Krishnamoorthy AP/MCA and Mrs.J.Shobana AP/MCA. E-certificates were mailed to all the participants