Target Audience
- MCA/M.Tech Students
- Working Professionals from Corporate
Test & Evaluation
1. During the program, the participants will have to take all the assignments given to them for better learning.
2. At the end of the program, a final assessment will be conducted.
Certification
1. All successful participants will be provided with a certificate of completion.
2. Students who do not complete the course / leave it midway will not be awarded any certificate.
Tentative Date & Schedule
New batch starting from 29th June 2020 for the live online tutorial session and doubt clearing sessions
Topics to be covered
1. Introduction to Machine Learning using scikit-learn days (1-8)
- Overview of Machine Learning
- Difference between AI, ML, and DL
- Applications of ML and DL
- Types of Machine Learning
- Linear Regression
- Logistic Regression
- Overfitting and underfitting
- K-Nearest Neighbor
- Cross-validation and Hyper-parameter tuning
- Confusion Matrix, Recall, Precision
- K-Means Clustering
2. Introduction To Artificial Neural Network days (9-13)
- What is Artificial Neural Network (ANN)?
- How Neural Network Works?
- Perceptron
- Multilayer Perceptron
- Feed Forward
- Gradient Descent and Stochastic Gradient Descent
- Backpropagation
3. Introduction To Deep Learning days (14-15)
- What is Deep Learning?
- Deep Learning Packages
- Deep Learning Applications
- Building Deep Learning Environment
- Installing TensorFlow Locally
- Working with Google Colab
4. Indtroduction to TensorFlow days (16-18)
- What is TensorFlow?
- TensorFlow 1.x V/S TensorFlow 2.x
- Placeholder, Variables, Constants
- Operations using TensorFlow
- Difference between TensorFlow and NumPy operations
- Computational Graph
- Visualizing Graph using Tensorboard
5. Activation Functions days (19-20)
- What are Activation Functions?
- Sigmoid Function,
- Hyperbolic Tangent Function (tanh)
- ReLU – Rectified Linear Unit
- Softmax Function
- Vanishing Gradient Problem
6. Building an Artificial Neural Network: A Case Study / An Example days (21-23)
- Understanding MNIST Dataset
- Initializing weights and biases
- Defining loss/cost Function
- Train the Neural Network
- Minimizing the loss by adjusting weights and biases
7. Modern Deep Learning Optimizers and Regularization days (24-30)
- SGD with Momentum
- RMSprop
- AdaGrad
- Adam
- Dropout Layers and Regularization
- Batch Normalization
8. Building Deep Neural Network Using Keras days (31-33)
- What is Keras?
- Keras Fundamental For Deep Learning
- Keras Sequential Model and Functional API
- Solve a Linear Regression and Classification Problem with Example
- Saving and Loading a Keras Model
9. Convolutional Neural Networks (CNNs) days (34-40)
- Introduction to CNN
- CNN Architecture
- Convolutional Operations
- Pooling, Stride, and Padding Operations
- Data Augmentation
- Building, Training and Evaluating First CNN Model
- Model Performance Optimization
- Autoencoders for CNN
- Transfer Learning
10. Recurrent Neural Networks (RNNs) days (41-46)
- Introduction to RNN
- RNN Architecture
- Types of RNN
- Implementing basic RNN in TensorFlow
- Need for LSTM and GRU
- Deep RNN
- Text Classification Using LSTM
11. Projects days (47-50)
- Sentiment analysis using RNN
- MNIST Handwritten digits classification using CNN
- Cat vs Dog Image classification
- Objects Detection from Yolov3
Sample Project:
(Hand Detection) |
(Cat Dog Classification) |
(MNIST Digit Prediction) |
(Autocomplete search query in Tensorflow) |
(ChatBot Using Tensorflow) |
(Neural Machine Translation NMT Using Tensorflow) |
(Text Extraction from Image) |