Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders von Atashgahi, Zahra, Sokar, Ghada, van der Lee, Tim, Mocanu, Elena, Mocanu, Decebal Constantin, Veldhuis, Raymond, Pechenizkiy, Mykola

Volltext

SpaceNet: Make Free Space for Continual Learning von Sokar, Ghada, Mocanu, Decebal Constantin, Pechenizkiy, Mykola

Volltext

Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks von Sokar, Ghada, Mocanu, Decebal Constantin, Pechenizkiy, Mykola

Volltext

Topological Insights into Sparse Neural Networks von Liu, Shiwei, Van der Lee, Tim, Yaman, Anil, Atashgahi, Zahra, Ferraro, Davide, Sokar, Ghada, Pechenizkiy, Mykola, Mocanu, Decebal Constantin

Volltext

Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks von Sokar, Ghada, Mocanu, Decebal Constantin, Pechenizkiy, Mykola

Volltext bestellen

The Dormant Neuron Phenomenon in Deep Reinforcement Learning von Sokar, Ghada, Agarwal, Rishabh, Castro, Pablo Samuel, Evci, Utku

Volltext bestellen

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL von Sokar, Ghada, Obando-Ceron, Johan, Courville, Aaron, Larochelle, Hugo, Castro, Pablo Samuel

Volltext bestellen

Where to Pay Attention in Sparse Training for Feature Selection? von Sokar, Ghada, Atashgahi, Zahra, Pechenizkiy, Mykola, Mocanu, Decebal Constantin

Volltext bestellen

Self-Attention Meta-Learner for Continual Learning von Sokar, Ghada, Mocanu, Decebal Constantin, Pechenizkiy, Mykola

Volltext bestellen

Learning Invariant Representation for Continual Learning von Sokar, Ghada, Mocanu, Decebal Constantin, Pechenizkiy, Mykola

Volltext bestellen

Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates von Yildirim, Murat Onur, Yildirim, Elif Ceren Gok, Sokar, Ghada, Mocanu, Decebal Constantin, Vanschoren, Joaquin

Volltext bestellen

Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning von Grooten, Bram, Sokar, Ghada, Dohare, Shibhansh, Mocanu, Elena, Taylor, Matthew E, Pechenizkiy, Mykola, Mocanu, Decebal Constantin

Volltext bestellen

SpaceNet: Make Free Space For Continual Learning von Sokar, Ghada, Decebal Constantin Mocanu, Pechenizkiy, Mykola

Volltext

Mixtures of Experts Unlock Parameter Scaling for Deep RL von Obando-Ceron, Johan, Sokar, Ghada, Willi, Timon, Lyle, Clare, Farebrother, Jesse, Foerster, Jakob, Dziugaite, Gintare Karolina, Precup, Doina, Castro, Pablo Samuel

Volltext bestellen

Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks von Sokar, Ghada, Decebal Constantin Mocanu, Pechenizkiy, Mykola

Volltext

Dynamic Sparse Training for Deep Reinforcement Learning von Sokar, Ghada, Mocanu, Elena, Mocanu, Decebal Constantin, Pechenizkiy, Mykola, Stone, Peter

Volltext bestellen

The Dormant Neuron Phenomenon in Deep Reinforcement Learning von Sokar, Ghada, Agarwal, Rishabh, Castro, Pablo Samuel, Evci, Utku

Volltext

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL von Sokar, Ghada, Obando-Ceron, Johan, Courville, Aaron, Larochelle, Hugo, Castro, Pablo Samuel

Volltext

Where to Pay Attention in Sparse Training for Feature Selection? von Sokar, Ghada, Atashgahi, Zahra, Pechenizkiy, Mykola, Decebal Constantin Mocanu

Volltext

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity von Liu, Shiwei, Chen, Tianlong, Atashgahi, Zahra, Chen, Xiaohan, Sokar, Ghada, Mocanu, Elena, Pechenizkiy, Mykola, Wang, Zhangyang, Mocanu, Decebal Constantin

Volltext bestellen