Nb. days
3
Face-to-face?
Yes
Remote?
Yes
Min. participants
2
Max. participants
8
Place
Toulouse, Paris, etc.
Pricing
2290€ HT
Artificial intelligence was created in the 1950s. After many winters, this science is currently experiencing a new boom. Machine Learning and in particular Deep Learning are at the origin of many advances in various fields (computer vision, natural language processing, etc.) applicable to all sectors of activity.
The increase in the volume of data and the computational power of the machines at our disposal now allow us to apply and improve the theories set out a few decades ago.
The increase in the volume of data and the computational power of the machines at our disposal now allow us to apply and improve the theories set out a few decades ago.
At the end of this training, you will know the fundamental principles of Deep Learning and you will master the different architectures of neural networks, allowing you to create models that meet your needs.
Goals
- Understanding Deep Learning
- Use Deep Learning frameworks: TensorFlow v2 and Keras
- Master the different neural network architectures: dense, convolutional, recurrent, generative
- Implement concrete cases for each type of network
- Run calculations on CPUs, GPUs and TPUs
- Measure the relevance of the implemented models & visualize the learning
- Deploy a model in production
To know the dates of the next training sessions,
to adapt this program to your needs
or to obtain additional information,
contact us!
to adapt this program to your needs
or to obtain additional information,
contact us!
Teaching method
- This training is 70% practical and uses illustrated and didactic exercises.
- A daily evaluation of the acquisition of the knowledge of the day before is carried out.
- A synthesis is proposed at the end of the training.
- An evaluation will be proposed to the trainee at the end of the course.
- A course support will be given to each participant including slides on the theory and exercises.
- A sign-in sheet for each half-day of attendance is provided at the end of the course as well as a certificate of completion if the trainee has attended the entire session.
- A follow-up and an exchange with the participants will take place a few days after the training.
Prerequisite
Knowledge of the Python language is required as well as knowledge of scientific libraries (numpy and pandas).Targets
- Data Analysts
- Data Engineers
- Data Scientists
- Developers
Evaluation
This training does not require a formal assessment of learningProgram
Machine Learning
- Machine Learning definition
- The 5 tribes of Machine Learning
- The several kinds of learning
- Learning and Inference
Demo: Machine Learning from A to Z
First steps in neurons
- The formal neuron
- The perceptron
- Activation functions
- Gradient Descent
Demo: Neural Network Playground
Hands on: My first neural network
TensorFlow and Keras
- TensorFlow History
- TensorFlow v2 & Keras
- Graph vs eager execution
- Cloud Computing / CPU / GPU / TPU
- TensorBoard
Demo: TensorBoard
Hands on: Number recognition (MNIST)
Convolutional Neural Network
- CNN vs the human visual cortex
- Convolution & pooling layers
- Activation functions
- CNN Architecture
- How a network learns?
- Some reference architectures
Demo: Number Recognition with CNN (MNIST)
Hands on: Image recognition'
Recurrent Neural Network
- RNN
- LSTM
- GRU
- Natural Language Processing: Embeddings & Word2vec
- Transformers
Hands on: Prévision de séries temporelles
Hands on: Text Generation
Deep Generative Models
- Unsupervised learning
- Auto-Encoders & VAE (Variational Auto-encoder)
- GANs
Demo: Playground GAN
Demo: Generation of realistic photos
Demo: Applying a style to a picture
