|
| 1 | Introduction to Deep Learning – An overview of the definition, history, fundamental concepts, and application areas of deep learning. | Introduction to Deep Learning – An overview of the definition, history, fundamental concepts, and application areas of deep learning. | |
| 2 | Fundamentals of Neural Networks – Examination of perceptrons, activation functions, and basic neural network architectures. | Fundamentals of Neural Networks – Examination of perceptrons, activation functions, and basic neural network architectures. | |
| 3 | Forward and Backpropagation – Implementation of forward and backward propagation algorithms for weight updates, and an introduction to gradient descent methods. | Forward and Backpropagation – Implementation of forward and backward propagation algorithms for weight updates, and an introduction to gradient descent methods. | |
| 4 | Data Preparation and Model Training – Managing data preprocessing, training and validation processes, and addressing issues of overfitting and underfitting. | Data Preparation and Model Training – Managing data preprocessing, training and validation processes, and addressing issues of overfitting and underfitting. | |
| 5 | Convolutional Neural Networks (CNN) – Basic principles of CNN architectures used in image processing and classification applications, along with practical examples. | Convolutional Neural Networks (CNN) – Basic principles of CNN architectures used in image processing and classification applications, along with practical examples. | |
| 6 | Recurrent Neural Networks (RNN) and LSTM – Key features of models such as RNN, LSTM, and GRU for working with sequential data, including practical applications. | Recurrent Neural Networks (RNN) and LSTM – Key features of models such as RNN, LSTM, and GRU for working with sequential data, including practical applications. | |
| 7 | Model Optimization – Utilizing optimization algorithms (SGD, Adam, etc.), tuning learning rates, and strategies to enhance model performance. | Model Optimization – Utilizing optimization algorithms (SGD, Adam, etc.), tuning learning rates, and strategies to enhance model performance. | |
| 8 | Regularization and Normalization Techniques – Enhancing model generalization using methods such as dropout and batch normalization. | Regularization and Normalization Techniques – Enhancing model generalization using methods such as dropout and batch normalization. | |
| 9 | Advanced Architectural Models – An introduction to advanced models such as Generative Adversarial Networks (GANs), Autoencoders, and Transformers, along with their core principles. | Advanced Architectural Models – An introduction to advanced models such as Generative Adversarial Networks (GANs), Autoencoders, and Transformers, along with their core principles. | |
| 10 | Transfer Learning and Pre-Trained Models – Application of transfer learning methods, using pre-trained models, and introducing fine-tuning techniques. | Transfer Learning and Pre-Trained Models – Application of transfer learning methods, using pre-trained models, and introducing fine-tuning techniques. | |
| 11 | Applied Project Development – Developing projects that address real-world problems, emphasizing teamwork and practical model applications. | Applied Project Development – Developing projects that address real-world problems, emphasizing teamwork and practical model applications. | |
| 12 | Project Presentation and Overall Evaluation – Final project presentations, an overall review of the course content, and a feedback session. | Project Presentation and Overall Evaluation – Final project presentations, an overall review of the course content, and a feedback session. | |