Piscine Pro AI
Develop practical skills in data preprocessing, visualization, and applying machine learning models such as regression, classification (Decision Trees, XGBoost), and neural networks (CNNs, RNNs).
Gain hands-on experience with key Python libraries including pandas, matplotlib, scikit-learn, numpy, seaborn, PyTorch, and Keras.
Learning Outcomes
- Gain hands-on proficiency in data preprocessing and manipulation techniques.
- Apply simple and multiple linear regression methods to analyze real-world datasets.
- Implement logistic regression and multinomial logistic regression models effectively for classification tasks.
- Acquire practical experience in utilizing Decision Trees and XGBoost algorithms for classification tasks.
- Design, train, and evaluate various neural network models, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)
- Utilize data visualization techniques to effectively communicate insights derived from machine learning models.
- Gain hands-on experience with essential libraries and tools such as pandas, matplotlib, scikit-learn, numpy, seaborn, PyTorch, and Keras.
Skills
Gain hands-on tools:
Google Colab, Python, R, and GPU-accelerated computing
Learning Style
42 Style (Peer-to-Peer, Project-Based, Gamified) - Onsite
Program Contents
Level 1: Introduction to AI projects, like implementing a linear regression model to predict a continuous variable from input data
Level 2: Discovering classification through logistic regression and other more advanced models
Level 3: More advanced AI projects, such as constructing a neural network model for image classification
Target Audience
This course is tailored for individuals with foundational knowledge in programming and AI who are eager to advance and deepen their understanding of AI and Machine Learning concepts and techniques.
