1 citations · 2 across the 8 of their papers we have counts for
9 papers
Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
Cristian Pérez-Corral, Alberto Fernández-Hernández, Jose I. Mestre +3
Despite the empirical success of DNN, their internal training dynamics remain difficult to characterize. In ReLU-based models, the activation pattern induced by a given input deter…
Why Is Dynamically Special in Adam
Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre +2
Adam has been at the core of large-scale training for almost a decade, yet the role of its two momentum parameters remains poorly understood. Recent work shows that tying $β_{1}=β_…
GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
Jose I. Mestre, Alberto Fernández-Hernández, Cristian Pérez-Corral +3
In this work we introduce GreenLightningAI (GLAI), a new architectural block designed as an alternative to conventional MLPs. The central idea is to separate two types of knowledge…
Sinusoidal Initialization, Time for a New Start
Alberto Fernández-Hernández, Jose I. Mestre, Manuel F. Dolz +2
Initialization plays a critical role in Deep Neural Network training, directly influencing convergence, stability, and generalization. Common approaches such as Glorot and He initi…
OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection
Alberto Fernández-Hernández, Jose I. Mestre, Manuel F. Dolz +2
We introduce the Overfitting-Underfitting Indicator (OUI), a novel tool for monitoring the training dynamics of Deep Neural Networks (DNNs) and identifying optimal regularization h…
GreenLightningAI: An Efficient AI System with Decoupled Structural and Quantitative Knowledge
Jose Duato, Jose I. Mestre, Manuel F. Dolz +1
The number and complexity of artificial intelligence (AI) applications is growing relentlessly. As a result, even with the many algorithmic and mathematical advances experienced ov…
Acoustic Echo Cancellation using Residual U-Nets
J. Silva-Rodríguez, M. F. Dolz, M. Ferrer +3
This paper presents an acoustic echo canceler based on a U-Net convolutional neural network for single-talk and double-talk scenarios. U-Net networks have previously been used in t…
High performance and energy efficient inference for deep learning on ARM processors
Adrián Castelló, Sergio Barrachina, Manuel F. Dolz +2
We evolve PyDTNN, a framework for distributed parallel training of Deep Neural Networks (DNNs), into an efficient inference tool for convolutional neural networks. Our optimization…
High Performance and Portable Convolution Operators for ARM-based Multicore Processors
Pablo San Juan, Adrián Castelló, Manuel F. Dolz +2
The considerable impact of Convolutional Neural Networks on many Artificial Intelligence tasks has led to the development of various high performance algorithms for the convolution…