Jesús García Fernández

Jesus Garcia Fernandez, Sander Keemink, Marcel van Gerven

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation through time (BPTT), the prevailing method, extends the backpropagation (BP) algorithm by unrolling the RNN over time. However, this approach suffers from significant drawbacks, including the need to interleave forward and backward phases and store exact gradient information. Furthermore, BPTT has been shown to struggle to propagate gradient information for long sequences, leading to vanishing gradients. An alternative strategy to using gradient-based methods like BPTT involves stochastically approximating gradients through perturbation-based methods. This learning approach is exceptionally simple, necessitating only forward passes in the network and a global reinforcement signal as feedback. Despite its simplicity, the random nature of its updates typically leads to inefficient optimization, limiting its effectiveness in training neural networks. In this study, we present a new approach to perturbation-based learning in RNNs whose performance is competitive with BPTT, while maintaining the inherent advantages over gradient-based learning. To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization. We subsequently conduct a range of experiments to validate our approach. Our results show similar performance, convergence time and scalability compared to BPTT, strongly outperforming standard node and weight perturbation methods. These findings suggest that perturbation-based learning methods offer a versatile alternative to gradient-based methods for training RNNs which can be ideally suited for neuromorphic computing applications

Jesus Garcia Fernandez, Nasir Ahmad, Marcel van Gerven

Learning is a fundamental property of intelligent systems, observed across biological organisms and engineered systems. While modern intelligent systems typically rely on gradient descent for learning, the need for exact gradients and complex information flow makes its implementation in biological and neuromorphic systems challenging. This has motivated the exploration of alternative learning mechanisms that can operate locally and do not rely on exact gradients. In this work, we introduce a novel approach that leverages noise in the parameters of the system and global reinforcement signals. Using an Ornstein-Uhlenbeck process with adaptive dynamics, our method balances exploration and exploitation during learning, driven by deviations from error predictions, akin to reward prediction error. Operating in continuous time, Orstein-Uhlenbeck adaptation (OUA) is proposed as a general mechanism for learning dynamic, time-evolving environments. We validate our approach across diverse tasks, including supervised learning and reinforcement learning in feedforward and recurrent systems. Additionally, we demonstrate that it can perform meta-learning, adjusting hyper-parameters autonomously. Our results indicate that OUA provides a viable alternative to traditional gradient-based methods, with potential applications in neuromorphic computing. It also hints at a possible mechanism for noise-driven learning in the brain, where stochastic neurotransmitter release may guide synaptic adjustments.

Jesús García Fernández, Nasir Ahmad, Marcel van Gerven

Iterative optimization is central to modern artificial intelligence (AI) and provides a crucial framework for understanding adaptive systems. This review provides a unified perspective on this subject, bridging classic theory with neural network training and biological learning. Although gradient-based methods, powered by the efficient but biologically implausible backpropagation (BP), dominate machine learning, their computational demands can hinder scalability in high-dimensional settings. In contrast, derivative-free or zeroth-order (ZO) optimization feature computationally lighter approaches that rely only on function evaluations and randomness. While generally less sample efficient, recent breakthroughs demonstrate that modern ZO methods can effectively approximate gradients and achieve performance competitive with BP in neural network models. This ZO paradigm is also particularly relevant for biology. Its core principles of random exploration (probing) and feedback-guided adaptation (reinforcing) parallel key mechanisms of biological learning, offering a mathematically principled perspective on how the brain learns. In this review, we begin by categorizing optimization approaches based on the order of derivative information they utilize, ranging from first-, second-, and higher-order gradient-based to ZO methods. We then explore how these methods are adapted to the unique challenges of neural network training and the resulting learning dynamics. Finally, we build upon these insights to view biological learning through an optimization lens, arguing that a ZO paradigm leverages the brain's intrinsic noise as a computational resource. This framework not only illuminates our understanding of natural intelligence but also holds vast implications for neuromorphic hardware, helping us design fast and energy-efficient AI systems that exploit intrinsic hardware noise.

Jesus Garcia Fernandez, Siamak Mehrkanoon

Weather nowcasting consists of predicting meteorological components in the short term at high spatial resolutions. Due to its influence in many human activities, accurate nowcasting has recently gained plenty of attention. In this paper, we treat the nowcasting problem as an image-to-image translation problem using satellite imagery. We introduce Broad-UNet, a novel architecture based on the core UNet model, to efficiently address this problem. In particular, the proposed Broad-UNet is equipped with asymmetric parallel convolutions as well as Atrous Spatial Pyramid Pooling (ASPP) module. In this way, The the Broad-UNet model learns more complex patterns by combining multi-scale features while using fewer parameters than the core UNet model. The proposed model is applied on two different nowcasting tasks, i.e. precipitation maps and cloud cover nowcasting. The obtained numerical results show that the introduced Broad-UNet model performs more accurate predictions compared to the other examined architectures.

Jesús García Fernández, Ismail Alaoui Abdellaoui, Siamak Mehrkanoon

The supply and demand of energy is influenced by meteorological conditions. The relevance of accurate weather forecasts increases as the demand for renewable energy sources increases. The energy providers and policy makers require weather information to make informed choices and establish optimal plans according to the operational objectives. Due to the recent development of deep learning techniques applied to satellite imagery, weather forecasting that uses remote sensing data has also been the subject of major progress. The present paper investigates multiple steps ahead frame prediction for coastal sea elements in the Netherlands using U-Net based architectures. Hourly data from the Copernicus observation programme spanned over a period of 2 years has been used to train the models and make the forecasting, including seasonal predictions. We propose a variation of the U-Net architecture and further extend this novel model using residual connections, parallel convolutions and asymmetric convolutions in order to introduce three additional architectures. In particular, we show that the architecture equipped with parallel and asymmetric convolutions as well as skip connections outperforms the other three discussed models.

Ismail Alaoui Abdellaoui, Jesus Garcia Fernandez, Caner Sahinli et al.

Neuroimaging techniques have shown to be useful when studying the brain's activity. This paper uses Magnetoencephalography (MEG) data, provided by the Human Connectome Project (HCP), in combination with various deep artificial neural network models to perform brain decoding. More specifically, here we investigate to which extent can we infer the task performed by a subject based on its MEG data. Three models based on compact convolution, combined convolutional and long short-term architecture as well as a model based on multi-view learning that aims at fusing the outputs of the two stream networks are proposed and examined. These models exploit the spatio-temporal MEG data for learning new representations that are used to decode the relevant tasks across subjects. In order to realize the most relevant features of the input signals, two attention mechanisms, i.e. self and global attention, are incorporated in all the models. The experimental results of cross subject multi-class classification on the studied MEG dataset show that the inclusion of attention improves the generalization of the models across subjects.