Skip to main content

Deep Learning and Applications

17999.00 INR 19999.00 INR

Deep Learning and Applications

You will understand how to design and implement deep neural networks for image classification and natural language processing.

Course Information

Welcome to the Deep Learning and Applications course! In this course, you will learn advanced topics in Artificial Intelligence and Machine Learning. You will understand how to design and implement deep neural networks for image classification and natural language processing. You will also learn about advanced techniques for data analysis, such as anomaly detection, clustering, and dimensionality reduction. The course is designed to benefit you in several ways. First, AI and ML are rapidly becoming critical fields for businesses to remain competitive. By taking this course, you will gain valuable knowledge and skills that can be applied in a variety of fields such as healthcare, finance, and manufacturing. Second, you will learn how to design and implement complex models, which is a highly sought-after skill in the current job market. Finally, the course will provide you with real-world learning opportunities through practical exercises and projects. You will learn how to apply your knowledge to solve real-world problems and build predictive models. This will help you develop your programming skills and give you the confidence to take on challenging projects. By the end of this course, you will have a solid understanding of advanced AI/ML concepts and be well-equipped to apply your skills to real-world problems.

    Course Content

  • Module-1

    Introduction to Deep Learning: Basics (00:27:56)

    Introduction to Deep Learning: Basics (00:08:25)

    System of Linear Equations (00:29:16)

    Row Echelon Form and Rank of Matrix (00:28:58)

    Vector Equations & Linear Span (00:33:36)

    Maxtrix-Vector Multiplication & Solving Matrix Equation (00:27:10)

    Test (00:00:00)

    DL Course Concept (00:01:20)

    Assignment Module1 (00:00:00)

  • Module-2

    Linear Dependence and Independence of Vectors (00:26:16)

    Linear Mapping & Matrix Mapping (00:27:44)

    Algebra of Matrix Multiplication & Transpose of Matrix (00:29:37)

    Invertible Matrx & their properties (00:28:12)

    Determinant of Matrices & their properties (00:16:55)

    Determinant of Matrices & their properties (00:08:41)

    Determinant of Matrices & their properties (00:08:04)

    Vector Space & Sub-Spaces (00:31:17)

    Vector Space & Sub-Spaces (00:05:20)

    Linear Independence, Basis & Dimension (00:26:39)

    Inner Products and Orthogonality (00:27:50)

    Eigenvalues & Eigenvectors (00:32:37)

    Diagonalisation of Matrices (00:25:03)

    Test (00:00:00)

    Assignment Module2 (00:00:00)

  • Module-3

    Singular Value Decomposition (SVD) (00:22:55)

    Basics of Probability Theory: Sets, Sample Spaces and Events (00:17:18)

    Basics of Probability Theory: Sets, Sample Spaces and Events (00:15:19)

    Probability Laws & Some Special Rules (00:29:35)

    Rules of Counting (00:32:24)

    Random Variable & Probability Mass Functions (00:32:04)

    Expectations & Associated Definitions (00:11:53)

    Expectations & Associated Definitions-2 (00:22:15)

    Conditional Expectations & Associated Rules (00:24:28)

    Continuous Random Variables & Probability Density Functions (00:33:53)

    Important Probability Density Functions & Bayes Rule (00:33:27)

    Some Useful Inequalities and Limit Theorems (00:35:33)

    Test (00:00:00)

    Assignment Module3 (00:00:00)

  • Module-4

    Some Estimation Technique (00:26:56)

    Optimisation: Gradient & Hessian of Function (00:30:59)

    Convex Function & Gradient Descent (00:31:04)

    Stochastic Gradient Descent: Mini-Batch SGD (00:26:54)

    Basics of Machine Learning (00:55:44)

    Error Function in Machine Learning (00:39:44)

    Regression & Ridge Regression (00:28:26)

    Support Vector Machine (00:34:32)

    Neural Networks: Introduction (00:30:11)

    Binary & Multi-Class Classification (00:30:28)

    Neural network Concept (00:02:16)

    Test (00:00:00)

    Assignment Module4 (00:00:00)

  • Module-5

    Feature Map & Logistic Regression (00:35:08)

    Backpropagation Algorithm (00:47:19)

    Multilayer Perception (00:39:32)

    Computer Vision: Introduction to CNN (00:33:00)

    Introduction to RNN (00:44:43)

    Review of FFNN (00:36:13)

    Forward and Backward Propagation in RNN (00:30:20)

    Back Propagation through TIme (00:20:57)

    Computer vision Concept (00:01:38)

    BP and GD Concept (00:01:26)

    Test (00:00:00)

    sequential modeling Concept (00:01:48)

    Assignment Module5 (00:00:00)

  • Module-6

    RNN Applications and Examples (00:26:12)

    RNN Applications and Examples (00:12:03)

    Introduction to LSTM (00:09:48)

    Introduction to LSTM (00:35:59)

    Leveraging Signal Processing to Deep Learning (00:20:52)

    Leveraging Signal Processing to Deep Learning (00:21:54)

    Comparison of LSTM and GRU (00:25:05)

    Time Delay Neural Network (00:24:18)

    Comparison of LSTM and GRU (00:17:33)

    Time Delay Neural Network (00:22:57)

    Comparison of LSTM and GRU (00:10:11)

    LSTMs Concept (00:01:26)

    RNNs and LSTMs Concept (00:02:56)

    Test (00:00:00)

    MT Concept (00:01:32)

    Assignment Module6 (00:00:00)

  • Module-7

    Introduction to CNN and Drawbacks of CNN (00:23:13)

    Introduction and Drawbacks to RNN and LSTM (00:24:19)

    Introduction to BERT (00:23:32)

    Introduction to Transformer (00:19:45)

    Attention Mechanism in Transformer (00:37:02)

    Introduction to Autoencoders (00:26:59)

    Regularization in Autoencoders (00:18:07)

    Alternative Training of DFNN (00:21:07)

    Alternative Training of DFNN (00:18:38)

    Introduction to Variational Autoencoders-2 (00:20:19)

    Introduction to Generative Adversarial Networks (00:22:20)

    Regularizer Concept (00:01:21)

    Generative Adversarial Networks Concept (00:01:29)

    Natural language processing Concept (00:02:00)

    Test (00:00:00)

    Introduction to Variational Autoencoders-1 (00:22:04)

    Training and testing loss Concept (00:01:40)

    Assignment Module7 (00:00:00)

  • Final Certification Examination

    Final Test (00:00:00)

Authors

Sumit Sah Profile

Sumit Sah

Sumit Sah, an ambitious Ph.D. scholar thriving in the dynamic realm of Electrical, Electronics, and Communication Engineering (EECE) at the esteemed Indian Institute of Technology, Dharwad. His academic journey is marked by a profound dedication to advancing the frontiers of knowledge in the world of technology. Sumit's current focus lies in the optimization of two cutting-edge domains: deep learning and federated learning. As a researcher, he delves into the intricacies of these fields, aiming to enhance their efficiency and applicability. His work is a testament to his commitment to pushing the boundaries of what is possible in the ever-evolving landscape of artificial intelligence. Equipped with a Master's degree in Mathematics from Banaras Hindu University, Sumit Sah brings a unique blend of skills to his research. His strong mathematical foundation serves as a solid pillar for addressing the complex challenges inherent in the field of deep learning. It is this interdisciplinary approach that sets Sumit apart, allowing him to navigate the intricate intersections of mathematics and technology with ease. Beyond the academic realm, Sumit is not just a scholar but a visionary seeking to make a tangible impact. His journey reflects a relentless pursuit of knowledge, a commitment to excellence, and a passion for unraveling the mysteries of advanced technologies. Sumit Sah is not just shaping his academic destiny; he is contributing to the collective progress of the scientific community. As he continues to make strides in his Ph.D. journey, the world anticipates the innovative solutions and breakthroughs that will undoubtedly emerge from his dedicated efforts.