This course introduces the basic concepts of deep learning and neural networks. It is intended for learners with a basic background in Python who are new to machine learning and AI.
Topics to be covered include:
• Key definitions and concepts in deep learning
• Neurons, neural networks, and multilayer perceptrons (MLPs)
• Introduction to TensorFlow or PyTorch: installation and simple examples
• Building simple models with Keras or PyTorch
• The training process: forward pass, loss functions, backpropagation
• Gradient Descent Algorithm and its variations, such as Stochastic Gradient Descent (SGD), Adam, and other common optimizers.
• Evaluating the performance of deep learning models.
• Using Keras/PyTorch and Scikit-learn for machine learning.
• Applying Dropout to prevent overfitting.
• Completing a practical project using a neural network in a Python environment.
Please email teh.rtc.reg@gmail.com for more information and instructions to apply. **Registration is only through email submission and approval by the Tehran-RTC**
Targeted Audience:
Weather forecasters and operational meteorologists interested in applying DL to forecasting./Researchers and scientists in meteorology and climate aiming to integrate DL into modeling or data analysis. Technical staff working with NWP, satellite data, or big datasets in meteorological services.Graduate students and early-career professionals in atmospheric sciences or related fields.
