Convolutional Neural Networks (CNN) for image recognition
Motivation and key-concepts (local connectivity, weight sharing)
Convolution: kernels, filters and feature maps
Aggregation, downsampling and pooling
Popular architectures: VGG, ResNet, GoogleNet
Image pre-processing
Using a pre trained neural network
Recurrent Neural Networks (RNN)
Motivation and key-concepts (windows size, memory, etc)
RNN most used architectures (LSTM, GRU), their losses and gradients
Discrete sequence: One hot encoding and embeddings
Application to classification
Application to sequence prediction
Representation learning
Autoencoders
Mutual information neural estimator
Deep Info Max
Contrastive Predictive Coding
Generative Models
Variational Autoencoders
GANs
Generation by reinforcement
Generation under condition
Style transfer
Evaluation of generative models
Advanced topics
Multi-task learning
Semi-supervised learning
Transfer learning
Debugging neural networks
Surround yourself with the best
Frédéric Paradis
Certified Trainer and Cloud Architect
As a certified Microsoft trainer, Frédéric describes himself as a Cloud magician who easily navigates the mythical space between technology and reality.
Marc Maisonneuve
Training program director
Marc Maisonneuve has acted as a Training Program Director, professional effectiveness trainer and user tools practice leader at AFI for several years. Mr. Maisonneuve is known for his analytical skills, his legendary calm and his undeniable desire to encourage people to develop their skills. He has the ability to present technological solutions in a natural way and to adapt them to the concrete needs of the workplace.
Vicky Moreau
Trainer
Vicky Moreau is a passionate freelancer and professional in the area of office automation. She holds a college diploma in office automation, most of her solid experience with the Office Suite was acquired while being an autodidact. In fact, she has successfully completed an MOS (Microsoft Office Specialist) Excel certification.
Francis Ferland-Stevenson
Trainer
Francis began as a trainer more than 5 years ago by testing office automation tools designed specifically to met the needs of his colleagues. His calm and his empathy makes him able to adapt his language according to the level of experience of the group. This makes his learnings clear and accessible to anyone. As a trainer, he is therefore attentive to the needs of his students to make sure they meet their objectives and face the challenges.