Machine Learning for Cognitive Systems Research Line
Contact: Juán Fernández Olivares
Contact: Juán Fernández Olivares
The primary aim of this research line is focused on improving the definition and development of mechanism and models applied to fields such as information access, filtering, retrieval and recommendation systems. This general objective can be broken down into the following challenges. On the one hand, to study new mechanisms to improve the current approaches […]
The knowledge is one of the outcomes of the humankind, and it is encoded in natural language, which is the main communication means of humans. The research line Natural Language Processing and Social Networks (NLP+SR) aims to enable computers to access to human knowledge by means the understanding and generation of language. The underlying information […]
In recent years, there has been an immense growth in data, leading to the Big Data. This requires large computing infrastructure with high performance processing capabilities. Getting large data ready for analysis and knowledge extraction is a difficult task and requires data to be pre-processed to improve the quality of the raw data. Data representation […]
Descriptive data mining techniques are aimed at describing the data or the phenomenon underlying the data, and are generally applied from the side of unsupervised learning. In this last paradigm, the data and properties of the sets to be analyzed are characterized by the absence of a label, class or output within them. Also indicate […]
The main goal of this research line is to create new theoretical and practical developments in the field of image and video processing and analysis. From a practical point of view, we employ multiple techniques (fully connected, convolutional, recurrent and generative adversarial networks, as well as geometric approaches that are not learning-based) to solve complex […]
As Machine Learning (ML) is applied to increasingly sensitive tasks, and applied to increasingly noisy data, it has become important that the algorithms we develop for the ML are robust for potentially noisy cases. In robust Machine Learning we address recent advances in a number of related topics, both theoretical and applied, including Learning in […]
In recent years, new problems and paradigms have appeared in Machine Learning, which, in some way, do not fit into the classical representation (input data vector, output value) or do not follow the conventional dynamics of classification and/or regression paradigms. Thus, as far as non-standard representations are concerned, in multi-instance learning (MIL), each pattern is […]
Artificial Intelligence (AI) offers increasingly precise algorithms that make it possible to analyse all kinds of data or signals, such as time series, images, text data, etc. With the emergence of applications, new needs have arisen which, along with precision, are fixed by the AI applications themselves and the problems they address. Among them, there […]
Blockchain is the underlying technology of all the crypto currencies that have been emerging in the first decades of the 21st century. This technology allows to create a ledger (formed by pieces of information or blocks) to store information. The most relevant characteristics of this ledger are It is distributed (in the form of peer […]
Federated Learning is a distributed learning paradigm which arises from both, the increasing awareness of data privacy and the growing number of smart devices connected to the internet. To sum up, Federated Learning consists of a set of clients which agree to train a learning model in a collaborative way under the orchestration of a […]
A time series is a set of data relating to the measurement of a magnitude (scalar or vector) ordered in time. It is a type of data of enormous interest that appears in all areas of knowledge and human activity. The immense variety in the nature of time series as well as the emergence of […]
At present, there is a growing trend on data generation, collection and processing in many different application areas, namely health, economics, and mainly IoT. In this context, Data Science and Big Data Analytics have emerged as complementary areas with the aim of extracting knowledge from this vast amount of information. In addition, the establishment of […]