Course intended for
Training course is aimed at developers and data analysts who want to learn the concepts of deep neural networks.
The course objective is to equip participants with knowledge about deep neural networks. The participants will be able to program and debug deep neural networks, including convolutional and the recurrent neural networks. Neural network architecture discussed during the training will be presented by means of basic concepts of computer vision (classification) and processing of natural language (text classification and generation). Additionally, newest research along with the most popular uses of deep learning will be presented, such as automated generation of description for images and transfer learning techniques.
Course is conducted by trainers who have both practical experience in the application of deep neural networks in image and natural language processing, as well as excellent theoretical background gained during research work and participation in international workshops. Training curriculum is regularly updated, after most important professional conferences (NIPS, ACL, EMNLP) or major competitions (ILSVRC, MSCOCO). Practical part of the training is conducted with the use of the open source software library TensorFlow.
Course requires basic programming skills in Python. In addition, participants will be expected to know the basic concepts of probability, linear algebra (matrix multiplication) and mathematical analysis (derivatives). Basic knowledge of machine learning (on the level of a PYTHON/ML course) would also be helpful.
4*8 hours (includes 1 hour of breaks each day) of lectures and workshops.
- Introduction to neural networks
- Deep learning vs machine learning
- Areas of application of neural networks
- Pros and cons of neural networks
- Neural networks fundamentals
- Neurons and multilayer perceptron
- Activation functions
- Learning process and optimization algorithms: SGD, Adagrad, Adadelta, Adam, RMSProp
- Neural networks for regression, classification and multilabel classification
- Neural networks maintenance
- Initialization of neural network parameters
- Batch Normalization
- Convolutional neural network
- Basic concepts: convolution, pooling, multilayer CNN
- Data augmentation for images
- Transfer learning
- Vector representation of words and documents
- Recurrent Neural Networks for natural language processing (NLP)
- Recurrent Neural Network
- Embedding layer
- Long Short-Term Memory
- Gated Recurrent Unit
- Multilayer RNNs
- Attention mechanism
- Non-sequential neural networks
- Multi-input neural networks
- Case studies
- Sentiment classification
- Image classification
- Text generation
- Image captioning: automated generation of descriptions for images