Deep Learning

This three-day training enables you to master the fundamentals and advanced techniques of deep learning. You will learn to design, train, and deploy neural networks to solve vision, natural language processing, and time-series problems using TensorFlow or PyTorch.

Learning Objectives:

• Understand the architecture and operation of multilayer perceptrons, CNNs, and RNNs.
• Set up a complete pipeline for training, validation, and testing.
• Apply deep learning to real-world cases: image classification, text analysis, and time-series forecasting.
• Optimize and tune hyperparameters to improve model performance.

Target Audience:
Data scientists, ML engineers, developers, and analysts aiming to advance their AI skills.

Duration:
3 days (9:00–12:30 & 13:30–17:00).

Number of Participants:
Maximum 12 participants.

Prerequisites:
Proficiency in Python and basic machine learning concepts (regression, random forests).

Program:

Day 1: Introduction & Multilayer Perceptrons

• Deep learning principles and history.
• Implement a multilayer perceptron with TensorFlow/PyTorch.
• Regularization techniques and activation functions.
• Workshop: simple image classification task.

Day 2: Convolutional Neural Networks

• CNN architecture and mechanics.
• Image preprocessing and data augmentation.
• Transfer learning and fine-tuning pre-trained models.
• Workshop: build a CNN pipeline for object recognition.

Day 3: Recurrent Networks & Advanced Applications

• RNN, LSTM, and GRU for text and time-series processing.
• NLP applications: text generation and sentiment classification.
• Best practices for model deployment and monitoring.
• Final workshop: mini-project combining vision and NLP.

Pricing:

• Open enrollment: €1,800 excl. VAT per participant
• In-house: on request, tailored to your needs

Methods Employed:

• Theoretical presentations and demonstrations
• Guided practical workshops
• Mini-project application

Evaluation:

• Positioning quiz and final assessment
• Mini-project review and personalized feedback

Accessibility:
Our sessions are accessible to people with disabilities. Please contact accessibility@eurekia-learning.com to arrange accommodations.

Contacts:

• Quality referent: Jihane Khouzaimi (06 69 53 77 75 – contact@eurekia-learning.com)
• Pedagogical referent: Hatim Khouzaimi

Note:
This intensive training will equip you with the tools to design and deploy high-performance deep learning models in real-world projects.