17 citations · 51 across the 31 of their papers we have counts for
10 papers · 1 filter
When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection
Mehmet Yamaç, Yagmur Mustu, Muhammad Numan Yousaf +2
Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal variation. Using the Pursuit of…
Axiomatizing Neural Networks via Pursuit of Subspaces
Mehmet Yamac, Mert Duman, Ugur Akpinar +4
While deep neural networks have achieved remarkable success across a wide range of domains, their underlying mechanisms remain poorly understood, and they are often regarded as bla…
Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies
David Leeftink, Max Hinne, Marcel van Gerven
A key capability of intelligent agents is to act effectively under incomplete state observations. Recurrent policies address this by compressing observation histories into a hidden…
Ornstein-Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines
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…
Subspace Node Pruning
Joshua Offergeld, Marcel van Gerven, Nasir Ahmad
Improving the efficiency of neural network inference is undeniably important in a time where commercial use of AI models increases daily. Node pruning is the art of removing comput…
Gradient-Free Training of Recurrent Neural Networks using Random Perturbations
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 tra…
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…
Neither hype nor gloom do DNNs justice
Felix A. Wichmann, Simon Kornblith, Robert Geirhos
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNN…
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…
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…