Formation en IA & Data: Advanced Deep Learning: from Transformers to Generative AI - Ascent Formation
Back to trainings
IA & Data

Advanced Deep Learning: from Transformers to Generative AI

5 jour(s)35h

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

    Advanced Deep Learning: from Transformers to Generative AI | Ascent Formation | Ascent Formation