Description
Master the fundamental and modern architectures of deep learning, from convolutional networks to Transformers, including LLM fine-tuning, generative models, and production optimization. Gain hands-on experience with PyTorch and the Hugging Face ecosystem.
Learning Objectives
- Master PyTorch as the primary deep learning framework.
- Understand and implement advanced CNN architectures and transfer learning.
- Gain in-depth knowledge of the attention mechanism and Transformer architecture.
- Fine-tune pre-trained language models using modern techniques (LoRA, QLoRA, Hugging Face).
- Understand generative architectures: VAEs, GANs, diffusion models.
- Master optimization and deployment techniques for production models.
Target Audience
Engineers and Developers aiming to master modern deep learning architectures
Data Scientists with a foundation in machine learning seeking to progress to deep learning
AI Project Managers and Consultants aiming to gain an in-depth technical understanding of models
Prerequisites
Solid knowledge of machine learning (supervised, unsupervised, model evaluation)
Practical experience with Python (numpy, pandas)
Understanding of statistics and linear algebra
Completion of the "Introduction to Deep Learning" training or equivalent knowledge
Program Outline
Informations
Duration
5 jour(s)
35h
Tarif
Sur demande
Similar Trainings
IA & Data
Cloud Migration
2 jour(s)
Sur demande
IA & Data
AI Agents – Designing Autonomous Systems with LangChain and LangGraph – Advanced
3 jour(s)
Sur demande
IA & Data
European AI Act — Understanding your obligations and ensuring compliance — Beginner level
1 jour(s)
Sur demande
IA & Data
Data Analysis with Microsoft Power BI (4-167)
3 jour(s)
2200 € HT