What will i learn?
Curriculum for this course
76 Lessons
00:00:00 Hours
Understanding AI
12 Lessons
00:00:00 Hours
- What is Artificial Intelligence 00:00:00
- What is Machine Learning 00:00:00
- How do machine builds the logic 00:00:00
- Machine Goal 00:00:00
- The World of Gradient Descent 00:00:00
- Derivative of a Function 00:00:00
- Linear Regression algorithm 00:00:00
- Working with machines 00:00:00
- Can machine have vision? 00:00:00
- Machine with vision 00:00:00
- Natural Language 00:00:00
- Learning Complex Games 00:00:00
Using Tensorflow
11 Lessons
00:00:00 Hours
- Installation Instructions
- What do we need for Machine Learning 00:00:00
- Building Hello World in Tensorflow 00:00:00
- Hello World in TensorFlow
- Understanding Computational Graph 00:00:00
- Computational Graph for Linear Regression 00:00:00
- Exercise:Boston housing Prices Predictor 00:00:00
- Data Normalization 00:00:00
- Exercise:Boston Housing Prices with Data Normalization 00:00:00
- Housing Predictor on Google Colab
- Housing Price Predictor
Simplify ML using Keras
18 Lessons
00:00:00 Hours
- Understanding role of Keras in Tensorflow 00:00:00
- keras vs tensorflow's lower level APIs 00:00:00
- Exercise Building Linear Regression model in keras 00:00:00
- Boston Housing Predictor in Keras
- Exercise_Using ML model for Prediction 00:00:00
- Predict Housing Prices using ML Model
- Assignment_How many Bikes are needed
- Regression vs Classification 00:00:00
- Math in Classification 00:00:00
- Using Softmax in Classification 00:00:00
- Loss and accuracy in Classification 00:00:00
- Exercise Classify handwritten numbers 00:00:00
- Hand-written digits Predictor with DL
- Mini batching in ML 00:00:00
- Ex_mini-batching in ML 00:00:00
- Mini-batching for MNIST Dataset
- Ex_Prediction using classification model 00:00:00
- improving ML model-hyperparameters 00:00:00
Deep Learning
17 Lessons
00:00:00 Hours
- Problem with Linear Algorithm 00:00:00
- How to capture complex logic 00:00:00
- What is Deep Learning 00:00:00
- Exercise: Deep Learning on MNIST Classification 00:00:00
- MNIST Classification with Deep Learning
- Using tensorboard_visualizing ML model 00:00:00
- Using TensorBoard
- Activation functions in Deep Learning 00:00:00
- Learning rate decay 00:00:00
- Dropout for overlifting 00:00:00
- optimizers momentum and nestrove momentum 00:00:00
- Adam,Adagrad Optimizers 00:00:00
- hyper parameters in deep learning 00:00:00
- Exercise_ReLu,Adam and dropout 00:00:00
- Applying ReLU, ADAM and Dropout
- Assignment CIFAR 10 Classification
- Convolution Neural network (CNN) and Pooling 00:00:00
Convolutional Neural Networks
7 Lessons
00:00:00 Hours
- problem with Dense Layers 00:00:00
- understanding convolutional layer 00:00:00
- Visualizing a Filter 00:00:00
- Filter Stride, Padding in convolutional layer 00:00:00
- Exercise CNN for MNIST Classification 00:00:00
- Using CNN for MNIST Classification
- Assignment CIFAR 10 Classification using CNN
Recurrent Neural Networks
11 Lessons
00:00:00 Hours
- Working with Textual Data 00:00:00
- TF IDF Vectorization 00:00:00
- Exercise Sentiment analysis with TF IDF 00:00:00
- Movie Reviews Sentiment Analysis
- Working with sequences 00:00:00
- Visualizing Recurrent Neural Network(RNN) 00:00:00
- Math of RNN 00:00:00
- Long short term memory (LSTM) cell 00:00:00
- Exercise LSTM for Sentiment Analysis 00:00:00
- Gated Recurrent Unit (GRU) 00:00:00
- Assignment: Reuters Newswire Classification
Requirements
+ View more
Description
+ View more
Other related courses
About the instructor
- 0 Reviews
- 784 Students
- 149 Courses
Student feedback
Reviews
Write a public review