EE-3310 - ATIT Academy

Please enable JavaScript to view the full PDF

International Course Outline Deep Learning with Python: A Complete Practical Course for Researchers [Online] Mentor Qais Yousef, Ph.D. in Systems Optimization and Applied Neuroscience, with 10+ years of experience in professional and academic fields. WhatsApp: +962795037290 Email: [email protected] Website: atitgroup.business.site Skype ID: ATITAcademy Youtube Channel: youtube.com/c/ATITAcademy Course Details ▪ Overview This course is for academic researchers to move with them step by step from scratch to advanced knowledge in the field of Deep Learning and its related topics that allow them to be able to implement their ideas and research findings. In this course, participants will learn Python and Deep Learning Neural Network from scratch then, based on a systematic learning methodology, will be able to increase their knowledge to a highly-advanced level. This intensive course is the only of its type that provides complete knowledge about almost all the cutting-edge aspects of Deep Learning, which allows the participants to be able to implement any type of related research in any area. Each participant will be worked with individually to start producing a respected project.  Total Time Around 33 Hours – 9 Sessions, between 3 to 4 hours long each. Workshop Sessions ▪ This comprehensive course will be covered over 9 sessions and contains the below topics: 1. Introduction to Artificial Intelligence and Deep Learning • What is Artificial Intelligence (AI) • What is Deep Learning (DL) • Types of DL algorithms: ➢ Convolution Neural Network (CNN) ➢ Recurrent Neural Network (RNN) ➢ Long Short-Term Memory (LSTM) ➢ Reinforcement Learning (RL) and Deep Q-Network (DQN) ➢ Generative Adversarial Network (GAN) • Applications on DL ATITAcademy Int’l. Amman, Jordan and Bochum, Germany. WhatsApp: +962795037290. Email: [email protected] International • Operations of DL • Practical Examples 2. Introduction to Python • Python Basics • Installing Python • PIP packages installer • Python Variables • Input and Output • If...Then...Else • Loops • Collections • Functions • Error Handling • Practical Project 3. Python for Deep Learning • Data Manipulation • Normalizing data • Formatting data • Important Python Packages for Image Processing and Deep Learning: ➢ OpenCV ➢ Tensorflow ➢ Keras ➢ Dlip • Practical Project 4. Optimization • Optimization Overview • DL as an optimization problem • Types of Optimizers (Teachers) • Optimization Approach Components • Formulating an Objective Function • Solving a maximization problem • Solving a minimization problem • Producing Convergence Curve • Practical Project on real functions 5. DNN Layers, Activation and Loss Functions • Input Layer • Hidden Layer: • Convolution Layers • Max pooling Layers • Classification Layer • Output Layer • Dropout Layer ATITAcademy Int’l. Amman, Jordan and Bochum, Germany. WhatsApp: +962795037290. Email: [email protected] International • Fully Connected Layers • Activation Functions: ➢ RELU ➢ Sigmoid ➢ Softmax • Loss Functions: ➢ Mean Square Error ➢ Cross-Entropy Loss • Practical Project 6. Classification Problem • Supervised Learning • Features Classification in Details • CNN in details • Classification Project 1 (General Dataset Selected by Participants) • Classification Project 2 (Medical Dataset) 7. Clustering Problem • Unsupervised Learning • Features Clustering in Details • Autoencoder algorithm in Details • Convolutional Autoencoder (Experimental) • Clustering Project (General Dataset Selected by Participants) 8. Regression Problem • Definition of Regression Problems • Simple Linear Regression • Multiple Regression • Assessing Performance • Ridge Regression • Feature Selection & Lasso • Nearest Neighbors & Kernel Regression • Practical project on using regression, for prediction 9. Other Deep Learning Techniques • Transfer Learning • Fine-tuning • Federated-learning • Deep Reinforcement Learning (Deep Q-Learning) • Generative Adversarial Neural Network (GANs) • Practical Project using Related Techniques on a Problem Selected by Participants ▪ A complete project will be assigned for participants in each session, (aside from the session-shared projects) to work on at home, and is required to submit it at the beginning of every session starting from the 2nd session. The submitted assignments will be discussed in the next session with each student individually. ▪ Questions and discussions are highly encouraged during the session. ATITAcademy Int’l. Amman, Jordan and Bochum, Germany. WhatsApp: +962795037290. Email: [email protected] International Remarks ▪ Each participant MUST have a suitable computer with a stable internet connection. ATITAcademy Int’l. Amman, Jordan and Bochum, Germany. WhatsApp: +962795037290. Email: [email protected]