Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551014
Pertenecen a esta colección Tesis y Trabajos de grado de los Doctorados correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- A generalist reinforcement learning agent for compressing multiple convolutional neural networks(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12-11) González Sahagún, Gabriel; Conant ablos, Santiago Enrique; emipsanchez; Ortíz Bayliss, José Carlos; Cruz Duarte, Jorge Mario; Gutiérrez Rodríguez, Andrés Eduardo; School of Engineering and Sciences; Campus MonterreyDeep Learning has achieved state-of-the-art accuracy in multiple fields. A common practice in computer vision is to reuse a pre-trained model for a completely different dataset of the same type of task, a process known as transfer learning, which reduces training time by reusing the filters of the convolutional layers. However, while transfer learning can reduce training time, the model might overestimate the number of parameters needed for the new dataset. As models now achieve near-human performance or better, there is a growing need to reduce their size to facilitate deployment on devices with limited computational resources. Various compression techniques have been proposed to address this issue, but their effectiveness varies depending on hyperparameters. To navigate these options, researchers have worked on automating model compression. Some have proposed using reinforcement learning to teach a deep learning model how to compress another deep learning model. This study compares multiple approaches for automating the compression of convolutional neural networks and proposes a method for training a reinforcement learning agent that works across multiple datasets without the need for transfer learning. The agents were tested using leaveone- out cross-validation, learning to compress a set of LeNet-5 models and testing on another LeNet-5 model with different parameters. The metrics used to evaluate these solutions were accuracy loss and the number of parameters of the compressed model. The agents suggested compression schemes that were on or near the Pareto front for these metrics. Furthermore, the models were compressed by more than 80% with minimal accuracy loss in most cases. The significance of these results is that by escalating this methodology for larger models and datasets, an AI assistant for model compression similar to ChatGPT can be developed, potentially revolutionizing model compression practices and enabling advanced deployments in resource-constrained environments.
- A Deep Learning-based Algorithm for the Routing Problem in Vehicular Delay-Tolerant Networks(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020-06-11) Hernández Jiménez, Roberto; CARDENAS PEREZ, CESAR RAUL; 35258; HERNANDEZ JIMENEZ, ROBERTO; 454135; GONZALEZ MENDOZA, MIGUEL; 123361; SOSSA AZUELA, JUAN HUMBERTO; 7036; BUSTAMANTE BELLO, MARTIN ROGELIO; 58810; Cárdenas Pérez, César Raúl; ilquio; González Mendoza, Miguel; Sossa Azuela, Juan Humberto; Bustamante Bello, Martín Rogelio; Escuela de Ingeniería y Ciencias; Campus Estado de México; Muñoz Rodríguez, DavidThe exponential growth of cities across the world has brought along important challenges such as waste management, pollution and overpopulation, and transportation administration. To mitigate these problems, the idea of Smart City was born, seeking to provide robust solutions integrating sensors and electronics, information technologies and communication networks. More particularly, to face transportation challenges, Intelligent Transportation Systems are a vital component in this quest. Intelligent Transportation Systems are intelligent systems that aim at providing the best solution to transportation-related matters, with the aid of information technologies, electrical and electronics and communication networks. In this context, communication networks are called Vehicular Networks, and they offer a communication framework for moving vehicles, road infrastructure and pedestrians. The extreme conditions of vehicular environments, nonetheless, make communication between high-speed moving nodes very difficult, so non-deterministic approaches are necessary to maximize the chances of packet delivery. In this work, this problem is addressed using Artificial Intelligence from a hybrid perspective, focusing on both the best next message to replicate and the best next hop in its path in the network. Furthermore, DLR+ is proposed, a router with a prioritized type of message scheduler and a routing algorithm based on Deep Learning. Simulations done to assess the router performance show important gains in terms of network overhead and hop count, while maintaining an acceptable packet delivery ratio and delivery delays, with respect to other popular routing protocols in vehicular networks.
- Unsupervised Deep Learning Recurrent Model for Audio Fingerprinting(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020-04-16) Báez Suárez, Abraham; BAEZ SUAREZ, ABRAHAM; 328083; Nolazco Flores, Juan Arturo; Vargas Rosales, César Vargas; Gutiérrez Rodríguez, Andrés Eduardo; Rodríguez Dagnino, Ramón Martín; Loyola González, Octavio; Escuela de Ingeniería y Ciencias; Campus MonterreyAudio fingerprinting techniques were developed to index and retrieve audio samples by comparing a content-based compact signature of the audio instead of the entire audio sample, thereby reducing memory and computational expense. Different techniques have been applied to create audio fingerprints, however, with the introduction of deep learning, new data-driven unsupervised approaches are available. This doctoral dissertation presents a Sequence-to-Sequence Autoencoder Model for Audio Fingerprinting (SAMAF) which improved hash generation through a novel loss function composed of terms: Mean Square Error, minimizing the reconstruction error; Hash Loss, minimizing the distance between similar hashes and encouraging clustering; and Bitwise Entropy Loss, minimizing the variation inside the clusters. The performance of the model was assessed with a subset of VoxCeleb1 dataset, a "speech in-the-wild" dataset. Furthermore, the model was compared against three baselines: Dejavu, a Shazam-like algorithm; Robust Audio Fingerprinting System (RAFS), a Bit Error Rate (BER) methodology robust to time-frequency distortions and coding/decoding transformations; and Panako, a constellation algorithm-based adding time-frequency distortion resilience. Extensive empirical evidence showed that our approach outperformed all the baselines in the audio identification task and other classification tasks related to the attributes of the audio signal with an economical hash size of either 128 or 256 bits for one second of audio. Additionally, the developed technology was deployed into two 9-1-1 Emergency Operation Centers (EOCs), located in Palm Beach County (PBC) and Greater Harris County (GH), allowing us to evaluate the performance in real-time in an industrial environment.