Foundations of Deep Learning: Concepts and Applications
4.0
(0)
6 learners
What you'll learn
This course includes
- 44.3 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 66 lessons • 44.3 hours of video
Foundations of Deep Learning: Concepts and Applications
66 lessons
• 44.3 hours
Foundations of Deep Learning: Concepts and Applications
66 lessons
• 44.3 hours
- Lec 65 GANs and Diffusion models demo -TA 37:38
- Lec 64 Diffusion Models for Generative Modelling 33:39
- Lec 63 LLMs demo -TA 39:48
- Lec 62 Evaluation, Benchmarking, and Impact of Foundation Models 20:53
- Lec 61 Reasoning, Retrieval, and Efficiency in Post-trained LLMs 45:11
- Lec 60 Reinforcement Learning for Aligning Large Language Models 26:20
- Lec 59 Pre-training and Instruction Tuning of Large Language Models 26:14
- Lec 58 Large Language Models: Tokenization, Generation, and Sampling 43:51
- Lec 57 In-context learning and Self-Supervised Learning in LLMs 34:48
- Lec 56 Transformer Architectures and Attention Mechanisms 28:37
- Lec 55 Foundations of Language Modeling and Transformers 41:10
- Lec 54 Hands-on implemenation of Autoencoders 47:50
- Lec 53 Reparameterization Trick 24:06
- Lec 52 VAE Architecture - Decoder part 42:09
- Lec 51 VAE Architecture - Encoder part 33:29
- Lec 50 Types of Autoencoders 47:40
- Lec 49 Introduction to Autoencoders 57:33
- Lec 48 Hands-on implementation of RNN in NLP application 30:08
- Lec 47 Word Embeddings in NLP 28:37
- Lec 46 Discrete and Distributed Word Representation 35:57
- Lec 45 Text Preprocessing and Text Representations 37:23
- Lec 44 Introduction to NLP 35:48
- Lec 43 Hands-on implementation of LSTM 36:21
- Lec 42 LSTM with attention 39:47
- Lec 41 LSTM-Encoder Decoder Structure 34:18
- Lec 40 Gated Recurrent Unit 18:22
- Lec 39 Introduction to LSTM 37:36
- Lec 38 Hands-on implementation of RNN model and its variants. 01:09:37
- Lec 37 Backpropagation through time (BTT) 01:00:01
- Lec 36 Vanishing and exploding gradients in NN 52:14
- Lec 35 Numerical Example for RNN 38:22
- Lec 34 Introduction to Recurrent Neural Networks 53:30
- Lec 33 Hands-on implemenation of YOLO 32:30
- Lec 32 Creating .yaml file for the custom dataset 18:52
- Lec 31 Hands-on implemenation of Unet 39:31
- Lec 30 YOLO v1 for object detection 25:35
- Lec 29 Object detection 47:28
- Lec 28 U-Net with Attention andEvaluation Metric for Segmentation 36:58
- Lec 27 Image segmentation 38:00
- Lec 26 Hands-on implemenation of XAI methods 24:41
- Lec 25 Grad-CAM and Class Activation Maps (CAMs) 49:31
- Lec 24 Guided backpropagation 53:56
- Lec 23 SHAP and LIME 01:05:57
- Lec 22 Need for XAI, PCI, Occlusion method 39:00
- Lec 21 Hands-on on building and deep CNN ensemble model. 39:17
- Lec 20 Hands-on on standard CNN architectures and transfer learning 40:58
- Lec 19 Introduction to Transfer Learning 17:28
- Lec 18 Introduction to ResNet (ResNet 34 and ResNet50) 30:51
- Lec 17 VGGNet (VGG16 and VGG19) and GoogleNet 33:28
- Lec 16 Architecture and Implementation of AlexNet 30:43
- Lec 15 Hands-on session on building simple CNN model 56:26
- Lec 14 Batch Normalization 46:58
- Lec 13 Convolution for RGB, Pooling Layer and Flatten Layer 01:14:36
- Lec 12 Introduction to Convolutional Neural Networks, Inspiration behind CNN, Key Components of CNN 58:22
- Lec 11 Fundamentals of Image representation and Image preprocessing and Data augmentation 01:06:01
- Lec 10 Hands-on on MLP for classification problem 01:06:48
- Lec 09 Regularization techniques in Neural Networks 38:39
- Lec 08 Varients of Gradient descent and Momentum based techniques 56:50
- Lec 07 Backpropagation in Neural Network 37:31
- Lec 06 Gradient descent algorithm 37:28
- Lec 05 Activation and Loss Functions 51:08
- Lec 04 Multi-Layer Perceptron 29:42
- Lec 03 Hands-on on Single Layer Perceptron 45:18
- Lec 02 Single Layer Perceptron 56:00
- Lec 01 Overview of Machine Learning and Deep Learning 25:09
- Foundations of Deep Learning: Concepts and Applications (Intro) 04:44
Take this course with you
Download the app to continue lessons from your phone anytime.
