In recent years, natural language generative models have shown outstanding performance in text generation tasks. However, when facing specific tasks or particular requirements, they may exhibit poor performance or require adjustments that demand large amounts of additional data. This work introduces PAGE (Prompt Augmentation for text Generation Enhancement), a framework designed to assist these models through the use of simple auxiliary modules. These modules, lightweight models such as classifiers or extractors, provide inferences from the input text. The output of these auxiliaries is then used to construct an enriched input that improves the quality and controllability of the generation. Unlike other generation-assistance approaches, PAGE does not require auxiliary generative models; instead, it proposes a simpler, modular architecture that is easy to adapt to different tasks. This paper presents the proposal, its components and architecture, and reports a proof of concept in the domain of requirements engineering, where an auxiliary module with a classifier is used to improve the quality of software requirements generation.

Currently, digital security mechanisms like Anomaly Detection Systems using Autoencoders (AE) show great potential for bypassing problems intrinsic to the data, such as data imbalance. Because AE use a non-trivial and nonstandardized separation threshold to classify the extracted reconstruction error, the definition of this threshold directly impacts the performance of the detection process. Thus, this work proposes the automatic definition of this threshold using some machine learning algorithms. For this, three algorithms were evaluated: the K-Nearst Neighbors, the K-Means and the Support Vector Machine.

The growing threat posed by deepfake videos, capable of manipulating realities and disseminating misinformation, drives the urgent need for effective detection methods. This work investigates and compares different approaches for identifying deepfakes, focusing on the GenConViT model and its performance relative to other architectures present in the DeepfakeBenchmark. To contextualize the research, the social and legal impacts of deepfakes are addressed, as well as the technical fundamentals of their creation and detection, including digital image processing, machine learning, and artificial neural networks, with emphasis on Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and Transformers. The performance evaluation of the models was conducted using relevant metrics and new datasets established in the literature, such as WildDeep-fake and DeepSpeak, aiming to identify the most effective tools in the battle against misinformation and media manipulation. The obtained results indicated that GenConViT, after fine-tuning, exhibited superior performance in terms of accuracy (93.82%) and generalization capacity, surpassing other architectures in the DeepfakeBenchmark on the DeepSpeak dataset. This study contributes to the advancement of deepfake detection techniques, offering contributions to the development of more robust and effective solutions against the dissemination of false information.

The field of quantum machine learning is a promising way to lead to a revolution in intelligent data processing methods. In this way, a hybrid learning method based on classic kernel methods is proposed. This proposal also requires the development of a quantum algorithm for the calculation of internal products between vectors of continuous values. In order for this to be possible, it was necessary to make adaptations to the classic kernel method, since it is necessary to consider the limitations imposed by the Hilbert space of the quantum processor. As a test case, we applied this new algorithm to learn to classify whether new points generated randomly, in a finite square located under a plane, were found inside or outside a circle located inside this square. It was found that the algorithm was able to correctly detect new points in 99% of the samples tested, with a small difference due to considering the radius slightly larger than the ideal. However, the kernel method was able to perform classifications correctly, as well as the internal product algorithm successfully performed the internal product calculations using quantum resources. Thus, the present work represents a contribution to the area, proposing a new model of machine learning accessible to both physicists and computer scientists.

Transformers are a neural network architecture originally designed for natural language processing that it is now a mainstream tool for solving a wide variety of problems, including natural language processing, sound, image, reinforcement learning, and other problems with heterogeneous input data. Its distinctive feature is its self-attention system, based on attention to one's own sequence, which derives from the previously introduced attention system. This article provides the reader with the necessary context to understand the most recent research articles and presents the mathematical and algorithmic foundations of the elements that make up this type of network. The different components that make up this architecture and the variations that may exist are also studied, as well as some applications of the transformer models. This article is in Spanish to bring this scientific knowledge to the Spanish-speaking community.

VAEs are probabilistic graphical models based on neural networks that allow the coding of input data in a latent space formed by simpler probability distributions and the reconstruction, based on such latent variables, of the source data. After training, the reconstruction network, called decoder, is capable of generating new elements belonging to a close distribution, ideally equal to the original one. This article has been written in Spanish to facilitate the arrival of this scientific knowledge to the Spanish-speaking community.

Deep Learning methods are currently the state-of-the-art in many problems which can be tackled via machine learning, in particular classification problems. However there is still lack of understanding on how those methods work, why they work and what are the limitations involved in using them. In this chapter we will describe in detail the transition from shallow to deep networks, include examples of code on how to implement them, as well as the main issues one faces when training a deep network. Afterwards, we introduce some theoretical background behind the use of deep models, and discuss their limitations. Training restricted boltzmann machines: An introduction.

These handouts are designed for people who is just starting involved with the topic artificial neural networks. We show how it works a single artificial neuron (McCulloch & Pitt model), mathematically and graphically. We do explain the delta rule, a learning algorithm to find the neuron weights. We also present some examples in MATLAB/Octave. There are examples for classification task for lineal and non-lineal problems. At the end, we present an artificial neural network, a feed-forward neural network along its learning algorithm backpropagation. ----- Estos apuntes est\'an dise\~nados para personas que por primera vez se introducen en el tema de las redes neuronales artificiales. Se muestra el funcionamiento b\'asico de una neurona, matem\'aticamente y gr\'aficamente. Se explica la Regla Delta, algoritmo deaprendizaje para encontrar los pesos de una neurona. Tambi\'en se muestran ejemplos en MATLAB/Octave. Hay ejemplos para problemas de clasificaci\'on, para problemas lineales y no-lineales. En la parte final se muestra la arquitectura de red neuronal artificial conocida como backpropagation.