Summer Internship On - Full Stack Deep Learning & Neural Network Development

• Role of Machine Learning in field of Artificial Intelligence
• Deep Learning v/s Machine Learning
• Brief History of AI Recap: SL, UL and RL
• Classification and regression in supervised learning,
• Clustering and association in unsupervised learning
• Algorithms that are used in these categories
• Introduction to AI and neural networks
• Deep Learning: Successes Last Decade
• What is AI and Deep Learning
• Discussion: Self-Driving Car Object Detection
• Applications of Deep Learning
• Challenges of Deep Learning
• Discussion: Sentiment Analysis Using LSTM
• Fundamentals of statistics
• Hypothesis testing
• Probability distributions
• Hidden Markov models.

• Multi-layer network introduction
• Regularization
• Deep neural networks
• Overfitting and capacity
• Neural network hyperparameters
• Logic gates
• Neural network hyperparameters
• Different activation functions used in neural networks: - ReLu, Softmax, Sigmoid, and hyperbolic functions
• Back propagation, forward propagation, convergence, hyper parameters

• Various methods that are used to train artificial neural networks
• Perceptron learning rule
• Tuning the learning rate
• Regularization techniques
• Optimization techniques
• Stochastic process
• Vanishing gradients
• Transfer learning
• Dropout layer
• Regression techniques: - including Lasso L1 and Ridge L2
• Unsupervised pre-training

• Understanding how Deep Learning works
• Activation functions
• Illustrating perceptron
• Perceptron training
• Multi-layer perceptron
• Key parameters of perceptron
• TensorFlow
• Tensorflow and Its Ecosystem
• Python libraries in TensorFlow : - code basics, variables, constants, placeholders, graph visualization
• Use-case implementation
• Keras

• Keras high-level neural network for working on top of TensorFlow
• Defining complex multi-output models
• Composing models using Keras
• Sequential and functional composition
• Batch normalization
• Deploying Keras with TensorBoard
• Neural network training process customization.
• Hands On: Build a Deep Learning Model Using Keras
• Hands On: Build a Deep Learning Model Using Tensorflow

• Using TFLearn API to implement neural networks
• Defining and composing models
• Deploying TensorBoard.
• DNNs (Deep Neural Networks)
• Introduction to deep neural networks (DNNs)
• Several building blocks of artificial neural networks (ANNs),
• The architecture of DNN and its building blocks
• Reinforcement learning in DNN concepts
• various parameters, layers, and optimization algorithms in DNN activation functions.
• Deep Neural Net optimization, tuning, interpretability
• Optimization Algorithms
• SGD, Momentum, NAG, Adagrad, Adadelta , RMSprop, Adam
• Hands on Exercise: MNIST Dataset
• Batch Normalization
• Understanding Exploding and Vanishing Gradients
• Hyperparameter Tuning
• Interpretability
• Width vs Depth

• What is a convolutional neural network?
• Understanding the architecture and use-cases of CNN
• Pooling layers
• Visualize CNN
• How to fine-tune a convolutional neural network
• Transfer learning
• Understanding recurrent neural networks
• Kernel filter
• Feature maps, and pooling
• Deploying convolutional neural networks in TensorFlow.

• Introduction to unstructured data
• Working with Image and Video
• Image feature extraction & analysis
• Image feature engineering
• Creating Image feature matrix
• Using Image features for Deep Neural Network
• Facial Image Recognition
• Object detection Model

• User Interface for face detection
• User Interface for object detection
• Model Deployment for face and object detection
• Server Deployment of model

Develop and deploy a model to identify a person wearing a mask or not wearing it.

During Covid Pandemic Mask becomes a new Normal. This project will be a good hands on experience on neural network and Open CV for image and video analysis. We will develop an end to end solution for identifying a face with a mask weared properly and generate an alarm if not. It will be developed from scratch to deployment stage with proper UI creation.

Develop a project to identify facial expressions of a human.

Facial expressions can play an important tool for collecting feedback for any service provided and understanding sentiments of a client or creating security solutions while driving. We will develop a neural network and computer vision project which can identify a user's facial expression after taking some service or a driver who is driving to identify if he feels sleepy while driving to generate alarm.

Make a prediction model to predict handwritten characters or numbers.

Here you will get hands-on experience with how to use features of images for building up predictive model. We will develop a CNN model using features of hand written images of characters or numbers to make a prediction over future input values by the user in the form of random images.

Build a model to identify an object using captured images.

This project will be built up using Tensorflow and CNN to best analyse an image after the training given to the model. You need to train a model, make the losses to the least possible value and distribution of activation and gradients. Complete feature engineering over unstructured data sets will be understood and practised on completion of this hands-on experience.