Neural Networks Training in Nantes

This instructor-led live training in Nantes (online or onsite) is aimed at advanced-level professionals who wish to explore state-of-the-art XAI techniques for deep learning models, with a focus on building interpretable AI systems.

By the end of this training, participants will be able to:

• Understand the challenges of explainability in deep learning.
• Implement advanced XAI techniques for neural networks.
• Interpret decisions made by deep learning models.
• Evaluate the trade-offs between performance and transparency.

This is a 4-day course introducing AI and its applications using the Python programming language. There is an option to have an additional day to undertake an AI project upon completion of this course.

Deep Reinforcement Learning (DRL) merges reinforcement learning concepts with deep learning models, empowering agents to make decisions by interacting with their surroundings. This technology drives many modern AI innovations, including self-driving cars, robotic control systems, algorithmic trading, and adaptive recommendation engines. DRL enables artificial agents to learn strategies, refine policies, and make autonomous choices through trial and error, guided by reward-based feedback.

This instructor-led training, available online or onsite, targets intermediate-level developers and data scientists eager to master and apply Deep Reinforcement Learning techniques. Participants will learn to build intelligent agents capable of making autonomous decisions in complex environments.

Upon completion of this training, participants will be able to:

• Grasp the theoretical foundations and mathematical principles underlying Reinforcement Learning.
• Implement core RL algorithms, including Q-Learning, Policy Gradients, and Actor-Critic methods.
• Construct and train Deep Reinforcement Learning agents using TensorFlow or PyTorch.
• Apply DRL to practical scenarios such as gaming, robotics, and decision optimization.
• Troubleshoot, visualize, and enhance training performance using contemporary tools.

Format of the Course also allows for the evaluation of participants.

• Interactive lectures accompanied by guided discussions.
• Hands-on exercises and practical implementation tasks.
• Live coding demonstrations and project-based applications.

Course Customization Options

• To request a customized version of this course (for example, utilizing PyTorch instead of TensorFlow), please contact us to make arrangements.

This program has been designed for managers, solutions architects, innovation officers, CTOs, software architects, and anyone interested in gaining an understanding of applied artificial intelligence and its near-term development trends.

This course explores the application of AI, with a focus on Machine Learning and Deep Learning, within the automotive industry. It aids in identifying technologies suitable for various in-vehicle scenarios, ranging from basic automation and image recognition to autonomous decision-making processes.

An Artificial Neural Network is a computational data model utilized in creating Artificial Intelligence (AI) systems capable of executing "intelligent" tasks. Neural Networks are frequently employed in Machine Learning (ML) applications, which constitute one implementation of AI. Deep Learning represents a specialized subset of ML.

This four-day course provides an introduction to Artificial Intelligence and its practical applications. Participants also have the option to extend the training by one additional day to work on a hands-on AI project upon completion of the course.

This instructor-led, live training in Nantes (online or onsite) is designed for intermediate-level data scientists and statisticians who aim to effectively prepare data, build models, and apply machine learning techniques within their respective fields.

Upon completion of this training, participants will be able to:

• Comprehend and implement a variety of Machine Learning algorithms.
• Prepare data and models for machine learning applications.
• Perform post hoc analyses and visualize results effectively.
• Apply machine learning techniques to real-world, sector-specific scenarios.

An Artificial Neural Network is a computational data model utilized in the development of Artificial Intelligence (AI) systems that can perform 'intelligent' tasks. Neural Networks are frequently employed in Machine Learning (ML) applications, which represent one form of AI implementation. Deep Learning constitutes a subset of Machine Learning.

This instructor-led live training in Nantes (online or onsite) is aimed at researchers and developers who wish to use Chainer to build and train neural networks in Python while making the code easy to debug.

By the end of this training, participants will be able to:

• Set up the necessary development environment to start developing neural network models.
• Define and implement neural network models using a comprehensible source code.
• Execute examples and modify existing algorithms to optimize deep learning training models while leveraging GPUs for high performance.

This instructor-led, live training in Nantes (online or on-site) provides an introduction into the field of pattern recognition and machine learning. It touches on practical applications in statistics, computer science, signal processing, computer vision, data mining, and bioinformatics.

By the end of this training, participants will be able to:

• Apply core statistical methods to pattern recognition.
• Use key models like neural networks and kernel methods for data analysis.
• Implement advanced techniques for complex problem-solving.
• Improve prediction accuracy by combining different models.

Type: Theoretical training with predefined practical applications chosen in advance with the students using either Lasagne or Keras, depending on the pedagogical group.

Pedagogical method: Presentation, discussion, and case studies.

Artificial Intelligence, after revolutionizing numerous scientific fields, has begun to transform a wide range of economic sectors (industry, medicine, communication, etc.). However, its portrayal in major media often leans toward fantasy, far removed from the reality of what Machine Learning and Deep Learning actually entail. The objective of this training is to provide engineers who already have a solid grasp of computing tools (including a foundation in software programming) with an introduction to Deep Learning, its various specialized domains, and the main network architectures currently in existence. While mathematical foundations will be reviewed during the course, a level of mathematics equivalent to BAC+2 (two years of higher education) is recommended for greater comfort. It is technically possible to skip the mathematical focus and adopt a purely 'system' perspective, but this approach will significantly limit your understanding of the subject.

This course provides foundational knowledge on neural networks, machine learning algorithms, and the principles and applications of deep learning.

Part 1 (40%) of the training emphasizes fundamentals, enabling you to select the appropriate technology stack, such as TensorFlow, Caffe, Theano, DeepDrive, or Keras.

Part 2 (20%) introduces Theano, a Python library designed to simplify the development of deep learning models.

Part 3 (40%) focuses extensively on TensorFlow, Google's open-source software library API for deep learning. All examples and hands-on exercises will be conducted using TensorFlow.

Audience

This course is designed for engineers looking to utilize TensorFlow for their deep learning projects.

Upon completion of this course, participants will:

• possess a solid understanding of deep neural networks (DNN), CNNs, and RNNs
• comprehend TensorFlow’s architecture and deployment mechanisms
• be capable of managing installation, production environments, and architectural configurations
• be able to evaluate code quality, perform debugging, and monitor performance
• be proficient in implementing advanced production tasks such as training models, constructing graphs, and logging