Curriculum
- 10 Sections
- 71 Lessons
- 8 Weeks
Expanse all sectionsCollapse all sections
- Introduction to AI and Deep Learning6
- 1.0Lecture1.1 Introduction to Deep Learning
- 1.1Lecture1.2 Necessity of Deep Learning over Machine Learning
- 1.2Lecture1.3 History and evolution of various deep learning algorithms
- 1.3Lecture1.4 AI and how is Deep Learning one of the paths to AI in the recent era
- 1.4Lecture1.5 Types of Machine Learning and Deep Learning
- 1.5Lecture1.6 Why Deep Learning
- Master Deep Network18
- 2.0Lecture2.1 Working of a Deep Network
- 2.1Lecture2.2 What is Perceptron
- 2.2Lecture2.3 What is Neuron
- 2.3Lecture2.4 Sigmoid neuron
- 2.4Lecture2.5 Activation functions
- 2.5Lecture2.6 Cost function
- 2.6Lecture2.7 Optimization
- 2.7Lecture2.8 Dense networks
- 2.8Lecture2.9 Regularization
- 2.9Lecture2.10 Layered structures
- 2.10Lecture2.11 Types of layers
- 2.11Lecture2.12 Forward pass
- 2.12Lecture2.13 Back propagation – chain rule and evaluation metrics
- 2.13Lecture2.14 Gradient Descent
- 2.14Lecture2.15 SGD (for a SoftMax classifier example)
- 2.15Lecture2.16 Nestorov’s momentum
- 2.16Lecture2.17 RMSProp
- 2.17Lecture2.18 Adam
- Objective on Neural networks using TensorFlow20
- 3.0Lecture3.1 Introduction to TensorFlow
- 3.1Lecture3.2 Advantages of TensorFlow
- 3.2Lecture3.3 Vectorization
- 3.3Lecture3.4 Variable declaration
- 3.4Lecture3.5 Sessions
- 3.5Lecture3.6 Graphs
- 3.6Lecture3.7 Tensorboard
- 3.7Lecture3.8 Implementation of a simple Perceptron in TensorFlow
- 3.8Lecture3.9 Implementing a simple feed forward Neural Network in TensorFlow
- 3.9Lecture3.10 Various activation functions and their ranges
- 3.10Lecture3.11 Pros and cons of Activation functions
- 3.11Lecture3.12 Why to use specific activation function
- 3.12Lecture3.13 When is the usage of activation function
- 3.13Lecture3.14 What are the ones used in industry for specific tasks
- 3.14Lecture3.15 Correlations and Heatmaps
- 3.15Lecture3.16 Regression Problem Analysis
- 3.16Lecture3.17 Mathematical modelling of Regression Model
- 3.17Lecture3.18 Gradient Descent Algorithm
- 3.18Lecture3.19 Use cases
- 3.19Lecture3.20 Model Specification
- Knowledge on CNN5
- Knowledge on RNN5
- Keras4
- TFlearn4
- Different architectures and Performance Improvements7
- 8.0Lecture8.1 ConvNets architecture
- 8.1Lecture8.2 Performance evaluations
- 8.2Lecture8.3 Hyperparameter search
- 8.3Lecture8.4 Auto-monitoring of loss monitoring
- 8.4Lecture8.5 Input pre-processing
- 8.5Lecture8.6 Productionization of a deep learning pipeline
- 8.6Lecture8.7 Cloud workspace set-up for designing a prototype
- Building an AI application with Computer Vision1
- Building an AI application - Natural Language Processing1