Intelligence artificielle et données
488 documents à télécharger gratuitement
Cours, examens, TD, TP et exercices de intelligence artificielle et données. Thèmes couverts : machine learning, apprentissage automatique, big data, data science, fouille de données.
This document contains an exam focused on deep learning fundamentals with a specific emphasis on model training and evaluation techniques. It includes questions on dataset splitting, evaluation metrics, and neural network architectures. The document also poses practical problems requiring calculations, explanations, and identification of potential errors in code.
This document explores the concept of transfer learning, focusing on its ability to leverage pre-trained models for tasks with insufficient data. It details the methodology of applying deep transfer learning by reusing features from existing neural networks, specifically using VGG-19 in Keras. Practical examples like domain adaptation in image recognition and sentiment analysis are discussed, while a structured Python-based implementation for image processing tasks is provided. Key steps include freezing pre-trained layers and fine-tuning new layers to adapt the model to a target task.
This document discusses the concept of transfer learning in the context of machine learning and deep learning. It provides definitions, examples, and implementation strategies for building transfer learning models using Keras in Python. The focus is on leveraging knowledge from resource-rich domains to improve learning in low-resource tasks.
This document provides detailed instructions on implementing Convolutional Neural Networks (CNNs) using TensorFlow, starting with the MNIST dataset and progressing to the CIFAR-10 dataset. It covers concepts like data preprocessing, model creation, training, and evaluation. The methodology demonstrates building models with basic layers and CNN-specific layers like convolutional and pooling, optimizing with gradient descent and AdamOptimizer, achieving progressive accuracy improvements. Helper functions make data handling and model configuration efficient.
This document covers the fundamentals of Convolutional Neural Networks (CNNs) using Python and TensorFlow. It provides a step-by-step approach to working with the MNIST dataset, including data loading, visualization, model creation, and training. The document also explains how to implement the CNN architecture and evaluate its performance.
This document provides a systematic introduction to neural networks, beginning with the biological inspiration for perceptrons, mathematical foundations, and activation functions. It explains the construction of artificial neural networks and their representation in layers, highlighting key concepts such as cost functions for error evaluation and the gradient descent optimization algorithm. The integration of backpropagation for network-wide error correction and the implementation of these models using Python and TensorFlow are explored. Practical insights into supervised learning workflows...
This course introduces the foundational concepts of neural networks and deep learning. It covers the individual components of neural networks, including perceptrons, activation functions, and the mathematical representation of these models. The course will also include practical coding exercises using Python and TensorFlow to reinforce the theoretical aspects learned.
The document provides foundational knowledge about neural networks and TensorFlow, starting with manual implementation of basic components such as operations, variables, placeholders, and activation functions. It progresses into practical examples, including designing simple neural networks, implementing regression approaches, and applying techniques with real datasets. A comprehensive overview of TensorFlow basics, such as constants, operations, placeholders, matrices, and advanced techniques using custom graphs, complete this foundational guide to implementing deep learning models. Variou...
This document focuses on the automatic classification of 29 varieties of cheese based on their nutritional properties using two clustering techniques: Hierarchical Ascendant Classification (CAH) and k-Means. It provides a detailed methodology that includes loading and analyzing the dataset, detecting optimal class numbers, and interpreting clustering results using univariate, multivariate, and principal component analysis. The results demonstrate that cheese groups are primarily defined by lipid and protein content, and further analysis excluding an outlier group—the 'fresh cheeses'—yields...
Ce document décrit une démarche de classification automatique d'un ensemble de fromages basé sur leurs propriétés nutritives. Deux approches seront utilisées : la classification ascendante hiérarchique et la méthode des k-Means. Ce guide offre un aperçu pratique pour utiliser Python dans le contexte de la classification automatique.
This document explores unsupervised classification methods, focusing primarily on two types: hierarchical and non-hierarchical methods. It details the K-means algorithm, explaining its principles, convergence criteria, and the role of intra-class and inter-class variance. Hierarchical clustering is also discussed, describing dendrograms and aggregation criteria such as single linkage, complete linkage, and variance-based methods. Additionally, the document provides an overview of mixed classification, combining K-means partitioning with hierarchical clustering for a more refined analysis.
This document outlines methods of unsupervised classification, focusing on automatic classification techniques. It discusses the concepts of dissimilarity and inertia as they relate to grouping individuals based on their characteristics. Additionally, it presents the K-means algorithm for classifying data.
Ce document traite de l'analyse en composantes principales appliquée à un ensemble de données sur des véhicules. Il couvre les étapes d'importation des données, des statistiques descriptives, de la standardisation, de la création de la matrice de corrélation, et enfin de l'application de l'ACP. Les résultats montrent diverses corrélations entre les caractéristiques des voitures.
This document provides a practical demonstration of Correspondence Analysis (AFC) using R. A contingency table is created from qualitative variables, followed by row and column profile analysis using proportions. Chi-square tests are conducted to assess the independence of variables, and theoretical and empirical contingency tables are computed. The correspondence analysis (CA) is performed with two principal components for data visualization and interpretation.
This document presents a practical example of Correspondence Analysis (AFC) using R. It includes various steps to analyze a contingency table between two qualitative variables. The methods demonstrated include chi-squared tests and the calculation of profile tables.
This document focuses on the application of Correspondence Analysis (AFC), a statistical method for exploring relationships between categorical variables in contingency tables. The study examines the association between employee age categories and job roles through statistical tests, including a chi-squared test for independence. Key findings reveal significant dependence between these variables and associations like the proximity of 'Cadre' with '< 30 years.' Methodology involves construction and interpretation of line and column profiles, as well as visualizing relationships using multidi...
This document outlines the methodology and statistical analysis for the Factorial Correspondence Analysis (AFC) applied to two qualitative variables. It includes contingency tables representing the distribution of employees by age and category. The document further explores the relationships between these variables and tests for independence using the chi-squared test.
The document details the methodology for conducting Principal Component Analysis (PCA) on automobile data using Python. It involves data preparation by centering and scaling using the StandardScaler from scikit-learn. PCA is performed, and eigenvalues and explained variance are calculated to determine key components. Graphical tools such as the Scree plot and variance-explained graphs help identify two principal components to retain. Finally, the proximity between vehicle models is analyzed through factor coordinates and their contributions to the principal axes.
Ce document traite de l'utilisation de l'analyse en composantes principales (ACP) à l'aide de Python, et spécifiquement de la bibliothèque 'scikit-learn'. Il présente un ensemble de données sur les véhicules, en expliquant comment préparer et analyser ces données à l'aide de PCA. L'accent est mis sur l'importance de centrer et réduire les variables avant de procéder à l'ACP.
This document outlines a course workshop on data mining as part of the Business Analytics & Data Science master's program. It includes a section on principal component analysis (PCA) applied to vehicle data with specific tasks for analysis. The focus is on interpreting correlations and distributions of vehicles using PCA techniques.
The document outlines a practical workshop for Principal Component Analysis (PCA) applied to six continuous variables recorded from data on 20 cars. Using R programming and the FactoMineR and factoextra packages, correlations between variables are analyzed to identify patterns and influences in the factor space. The methodology includes generating a correlation matrix, interpreting factor axes, plotting correlation circles, and examining individual contributions. Results provide insights into the distribution of vehicles across the factor map, supported by graphical visualizations.
This document outlines an academic workshop focused on data mining techniques used within the context of business analytics and data science. It covers principal component analysis (PCA) of vehicle data, including tasks such as correlation analysis, factor interpretation, and data visualization techniques using R packages. Practical coding examples are provided to assist in performing PCA and interpreting results.
This document outlines the application of Principal Component Analysis (PCA) on a dataset containing six continuous variables related to 20 cars. The primary focus is on understanding correlations between variables using a correlation matrix and interpreting the first two PCA axes with the help of variable-factor correlations and a correlation circle. Additionally, distributions of cars are analyzed on the first factor plane using contributions and squared cosine values of observations. The analysis is conducted using SPAD software, with graphical outputs such as histograms and factor maps...
The document outlines essential methods and techniques in data exploration, specifically principal component analysis, correspondence analysis, and unsupervised classification methods. It emphasizes analytical frameworks and the use of advanced statistical tools for data interpretation. The methodology involves leveraging software such as R and Anaconda to process and visualize data effectively. The findings aim to improve understanding of complex datasets and inform business analytics strategies.