15 citations · 20 across the 6 of their papers we have counts for
6 papers
Decorrelation Speeds Up Vision Transformers
Kieran Carrigg, Rob van Gastel, Melda Yeghaian +3
Masked Autoencoder (MAE) pre-training of vision transformers (ViTs) yields strong performance in low-label data regimes but comes with substantial computational costs, making it im…
Decorrelated Soft Actor-Critic for Efficient Deep Reinforcement Learning
Burcu Küçükoğlu, Sander Dalm, Marcel van Gerven
The effectiveness of credit assignment in reinforcement learning (RL) when dealing with high-dimensional data is influenced by the success of representation learning via deep neura…
Efficient Deep Learning with Decorrelated Backpropagation
Sander Dalm, Joshua Offergeld, Nasir Ahmad +1
The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a signific…
Node Perturbation Can Effectively Train Multi-Layer Neural Networks
Sander Dalm, Marcel van Gerven, Nasir Ahmad
Backpropagation (BP) remains the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phase…
Establishing phone-pair co-usage by comparing mobility patterns
Wauter Bosma, Sander Dalm, Erwin van Eijk +5
In forensic investigations it is often of value to establish whether two phones were used by the same person during a given time period. We present a method that uses time and loca…
Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks
Sander Dalm, Nasir Ahmad, Luca Ambrogioni +1
Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the…