Marcelino Martínez-Sober

Iván Vallés-Pérez, Emilio Soria-Olivas, Marcelino Martínez-Sober et al.

Accurate and fast demand forecast is one of the hot topics in supply chain for enabling the precise execution of the corresponding downstream processes (inbound and outbound planning, inventory placement, network planning, etc). We develop three alternatives to tackle the problem of forecasting the customer sales at day/store/item level using deep learning techniques and the Corporación Favorita data set, published as part of a Kaggle competition. Our empirical results show how good performance can be achieved by using a simple sequence to sequence architecture with minimal data preprocessing effort. Additionally, we describe a training trick for making the model more time independent and hence improving generalization over time. The proposed solution achieves a RMSLE of around 0.54, which is competitive with other more specific solutions to the problem proposed in the Kaggle competition.

Iván Vallés-Pérez, Emilio Soria-Olivas, Marcelino Martínez-Sober et al.

In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus activation function on computer vision tasks the models generalize better than with other nonlinearities - up to a 15% accuracy increase in CIFAR100 and 4% in CIFAR10, relative to the best of the benchmark activations tested. With the proposed activation function the vanishing gradient and dying neurons problems disappear, because the derivative of the activation function is always 1 or -1. The simplicity of the proposed function and its derivative make this solution specially suitable for TinyML and hardware applications.

Diego Bonilla-Salvador, Marcelino Martínez-Sober, Joan Vila-Francés et al.

In the domain of vision-language integration, generating detailed image captions poses a significant challenge due to the lack of curated and rich datasets. This study introduces PixLore, a novel method that leverages Querying Transformers through the fine-tuning of the BLIP-2 model using the LoRa method on a standard commercial GPU. The followed approach, which involves training on a carefully assembled dataset from state-of-the-art Computer Vision models combined and augmented by ChatGPT, addresses the question of whether intricate image understanding can be achieved with an ensemble of smaller-scale models, referred to as Knowledge Stitching. Comparative evaluations against major models such as GPT-4 and Google Bard demonstrate that PixLore-2.7B, despite having considerably fewer parameters, is rated higher than the existing State-of-the-Art models in over half of the assessments. Precisely, PixLore outperform Bard and BLIP-2, which score approximately 35.18% and 27.98% lower than PixLore in the task of image captioning. This research not only presents a groundbreaking approach but also highlights the importance of well-curated datasets in enhancing the performance of smaller models.

Iván Vallés-Pérez, Juan Gómez-Sanchis, Marcelino Martínez-Sober et al.

The field of conversational agents is growing fast and there is an increasing need for algorithms that enhance natural interaction. In this work we show how we achieved state of the art results in the Keyword Spotting field by adapting and tweaking the Xception algorithm, which achieved outstanding results in several computer vision tasks. We obtained about 96\% accuracy when classifying audio clips belonging to 35 different categories, beating human annotation at the most complex tasks proposed.