Python - Convolutional neural networks

• Knowledge of Python programming at the PYTHON_INTRO course level, but knowledge at the PYTHON_ADV course level is an advantage
• Knowledge of the basics of data analysis at the level of the PYTHON_DATAAN course
• Knowledge of the basics of machine learning at the level of the PYTHON_ML_INTRO course
• Knowledge of the basics of neural networks at the level of the PYTHON_ML_NN course

• Professional explanation with practical examples, exercises on computers.

• Presentation of the subject matter in printed or online form.

Day 1:

• Introduction to convolutional networks and working with data
• Basics of convolutional networks
• Work with image data
• Convolution, max-pooling and other operations
• Training and testing of models
• Implementation of a simple convolutional network in PyTorch or TensorFlow

Day 2:

• Advanced convolutional networks
• Multilayer convolutional networks
• Reducing the dimensions of images in the network
• Regularization and overfitting
• Convolutional networks with residual blocks
• Transfer learning and the use of pre-trained models

Day 3:

• Solving problems in image processing
• Classification of images
• Object detection
• Image segmentation
• Practical exercises for solving these problems

Day 4:

• Practical use of convolutional networks
• Use of convolutional networks on specific applications
• Natural language processing using convolutional networks
• Speech recognition and the use of convolutional networks in audio applications
• Discussion on specific uses of convolutional networks in the participants' industry

Day 5:

• Optimization and expansion of convolutional networks
• Optimization and adjustment of network parameters
• Networks with variable architecture and design of new architectures
• Comparing the performance of different models
• Modification of convolutional networks for special cases, such as mobile devices or computers with limited resources
• Discussion on the future of convolutional networks and their applications
• Each day would include a theoretical part and practical exercises, where participants could use the learned techniques in practice
• Regenerate response

Previous courses

Python - data analysis (Pandas) [PYTHON_DATAN]

Python I - introduction to programming [PYTHON_INTRO]

Python - Introduction to Machine Learning [PYTHON_ML]

Python - Neural networks [PYTHON_ML_NN]

Next courses

Python - Backpropagation in neural networks [PYTHON_ML_BP]

Python - Deep Learning [PYTHON_ML_DP]