Catalogo dei Corsi di studio

Course website:

https://sites.google.com/di.uniroma1.it/aml-2023-2024

Google group:

https://groups.google.com/u/1/a/di.uniroma1.it/g/aml-23-24

Programme:

The course will present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It will include theory and practical coding, as well as a final hands-on project.

In a first part of the course, I will introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I will then showcase regression, as applied to detection (where the objects are in the image), pose estimation (whether people stand, sit or crunch) and re-identification (estimating a unique vector representation for each person). I will further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part will include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).

In a second part of the course, I will discuss generalization and the effective use of labelled and unlabelled data for learning. Further to transfer learning (how pre-trained models may be deployed for other tasks), I will discuss multi-modal (with different sensor modalities such as depth or thermal cameras) and self-supervision (e.g. training the DNN model by solving jigsaw puzzles) to auto-annotate large amounts of data. Also, I will present domain adaptation (e.g. apply daytime-detectors for night vision) and meta-learning, a most recent framework to learn how to learn a task, e.g. online or from little available data. Finally, I will introduce novel machine learning trends such as hyperbolic neural networks and generative diffusion models, and their applications to tasks such as anomaly detection while estimating the model uncertainty.

Course website:

https://sites.google.com/di.uniroma1.it/fds-2023-2024

Google group:

https://groups.google.com/u/1/a/di.uniroma1.it/g/fds-23-24

Programme:

The course is an introduction to the basics of Data Science as well as the relating topics from Data Mining, Machine Learning and Image Analysis, using the Python programming language.

I will cover the fundamental models, algorithms and approaches to deal with data from a Data Science and Machine Learning perspective, including the data preparation, the feature engineering, the model design and its optimization and evaluation. Topics from the course will include: basics of digital image processing, regression, classification with discriminative and generative models, optimization, bias/variance, regularization, clustering, dimensionality reduction, and a brief introduction to neural networks, including backpropagation and convolutional neural networks .

In the laboratory classes (for data science students only) I will introduce: the basics of Python, Numpy, data structures and Pandas, plotting, Scikit-learn, and sample programming of machine learning models from the course.

The course is an introduction to the basics of Data Science as well as the relating topics from Data Mining, Machine Learning and Image Analysis, using the Python programming language.

I will cover the fundamental models, algorithms and approaches to deal with data from a Data Science and Machine Learning perspective, including the data preparation, the feature engineering, the model design and its optimization and evaluation. Topics from the course will include: basics of digital image processing, regression, classification with discriminative and generative models, optimization, bias/variance, regularization, clustering, dimensionality reduction, and a brief introduction to neural networks.

In the laboratory classes (for data science students only) I will introduce: the basics of Python, Numpy, data structures and Pandas, plotting, Scikit-learn, and sample programming of machine learning models from the course.

For more information see the course website: https://sites.google.com/di.uniroma1.it/fds-2022-2023

The course will present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It will include theory and practical coding, as well as a final hands-on project.

In the first part of the course, I will introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I will then showcase regression, as applied to detection (where the objects are in the image), pose estimation (whether people stand, sit or crunch) and re-identification (estimating a unique vector representation for each person). I will further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part will include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).

In the second part of the course, I will discuss generalization and the effective use of labelled and unlabelled data for learning. Further to transfer learning (how pre-trained models may be deployed for other tasks), I will discuss multi-modal (with different sensor modalities such as depth or thermal cameras) and self-supervision (e.g. training the DNN model by solving jigsaw puzzles) to auto-annotate large amounts of data. Finally, I will present domain adaptation (e.g. apply daytime-detectors for night vision) and meta-learning, a most recent framework to learn how to learn a task, e.g. online or from little available data.

For more information see the course website: https://sites.google.com/di.uniroma1.it/aml-2022-2023

The course will present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It will include theory and practical coding, as well as a final hands-on project.

In the first part of the course, I will introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I will then showcase regression, as applied to detection (where the objects are in the image), pose estimation (whether people stand, sit or crunch) and re-identification (estimating a unique vector representation for each person). I will further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part will include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).

In the second part of the course, I will discuss generalization and the effective use of labelled and unlabelled data for learning. Further to transfer learning (how pre-trained models may be deployed for other tasks), I will discuss multi-modal (with different sensor modalities such as depth or thermal cameras) and self-supervision (e.g. training the DNN model by solving jigsaw puzzles) to auto-annotate large amounts of data. Finally, I will present domain adaptation (e.g. apply daytime-detectors for night vision) and meta-learning, a most recent framework to learn how to learn a task, e.g. online or from little available data.

For more information see the course website: https://sites.google.com/di.uniroma1.it/aml-2022-2023

The course is an introduction to the basics of Data Science as well as the relating topics from Data Mining, Machine Learning and Image Analysis, using the Python programming language.

I will cover the fundamental models, algorithms and approaches to deal with data from a Data Science and Machine Learning perspective, including the data preparation, the feature engineering, the model design and its optimization and evaluation. Topics from the course will include: basics of digital image processing, regression, classification with discriminative and generative models, optimization, bias/variance, regularization, clustering, dimensionality reduction, and a brief introduction to neural networks.

In the laboratory classes (for data science students only) I will introduce: the basics of Python, Numpy, data structures and Pandas, plotting, Scikit-learn, and sample programming of machine learning models from the course.

For more information see the course website: https://sites.google.com/di.uniroma1.it/fds-2022-2023