Lech Szymanski

According to our database, Lech Szymanski authored at least 31 papers between 2005 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

VASE: Variational Assorted Surprise Exploration for Reinforcement Learning.

Haitao Xu, Lech Szymanski, Brendan McCane

IEEE Trans. Neural Networks Learn. Syst., March, 2023

2022

Conceptual complexity of neural networks.

Lech Szymanski, Brendan McCane, Craig Atkinson

Neurocomputing, 2022

2021

Pseudo-rehearsal: Achieving deep reinforcement learning without catastrophic forgetting.

Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony V. Robins

Neurocomputing, 2021

Conceptual capacity and effective complexity of neural networks.

Lech Szymanski, Brendan McCane, Craig Atkinson

CoRR, 2021

Coarse facial feature detection in sheep.

Lech Szymanski, Michael Lee

Proceedings of the 36th International Conference on Image and Vision Computing New Zealand, 2021

2020

MIME: Mutual Information Minimisation Exploration.

Haitao Xu, Brendan McCane, Lech Szymanski, Craig Atkinson

CoRR, 2020

Deep Sheep: kinship assignment in livestock from facial images.

Lech Szymanski, Michael Lee

Proceedings of the 35th International Conference on Image and Vision Computing New Zealand, 2020

Predicting Cherry Quality Using Siamese Networks.

Yerren van Sint Annaland, Lech Szymanski, Steven Mills

Proceedings of the 35th International Conference on Image and Vision Computing New Zealand, 2020

2019

GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal.

Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony V. Robins

CoRR, 2019

Switched linear projections and inactive state sensitivity for deep neural network interpretability.

Lech Szymanski, Brendan McCane, Craig Atkinson

CoRR, 2019

A Convolutional Self-organizing Map for Visual Category Learning.

Chris Gorman, Lech Szymanski, Anthony V. Robins, Alistair Knott

Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

2018

Efficiency of deep networks for radially symmetric functions.

Brendan McCane, Lech Szymanski

Neurocomputing, 2018

The effect of the choice of neural network depth and breadth on the size of its hypothesis space.

Lech Szymanski, Brendan McCane, Michael H. Albert

CoRR, 2018

Some Approximation Bounds for Deep Networks.

Brendan McCane, Lech Szymanski

CoRR, 2018

Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks.

Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony V. Robins

CoRR, 2018

Stacked Hourglass CNN for Handwritten Character Location.

Hannah Clark-Younger, Steven Mills, Lech Szymanski

Proceedings of the 2018 International Conference on Image and Vision Computing New Zealand, 2018

Twin Bounded Large Margin Distribution Machine.

Haitao Xu, Brendan McCane, Lech Szymanski

Proceedings of the AI 2018: Advances in Artificial Intelligence, 2018

2017

Effects of the optimisation of the margin distribution on generalisation in deep architectures.

Lech Szymanski, Brendan McCane, Wei Gao, Zhi-Hua Zhou

CoRR, 2017

Deep Radial Kernel Networks: Approximating Radially Symmetric Functions with Deep Networks.

Brendan McCane, Lech Szymanski

CoRR, 2017

CNN for historic handwritten document search.

Lech Szymanski, Steven Mills

Proceedings of the 2017 International Conference on Image and Vision Computing New Zealand, 2017

Increasing the accuracy of convolutional neural networks with progressive reinitialisation.

Craig Atkinson, Brendan McCane, Lech Szymanski

Proceedings of the 2017 International Conference on Image and Vision Computing New Zealand, 2017

2016

SIFT10M.

Xiping Fu, Brendan McCane, Steven Mills, Michael H. Albert, Lech Szymanski

Dataset, February, 2016

Auto-JacoBin: Auto-encoder Jacobian Binary Hashing.

Xiping Fu, Brendan McCane, Steven Mills, Michael H. Albert, Lech Szymanski

CoRR, 2016

Deep networks are efficient for circular manifolds.

Brendan McCane, Lech Szymanski

Proceedings of the 23rd International Conference on Pattern Recognition, 2016

2014

Deep Networks are Effective Encoders of Periodicity.

Lech Szymanski, Brendan McCane

IEEE Trans. Neural Networks Learn. Syst., 2014

Hierarchical Structure from Motion from Endoscopic Video.

Steven Mills, Lech Szymanski, Reuben Johnson

Proceedings of the 29th International Conference on Image and Vision Computing New Zealand, 2014

2013

Singularity resolution for dimension reduction.

Shawn Martin, Lech Szymanski

Proceedings of the 28th International Conference on Image and Vision Computing New Zealand, 2013

Learning in deep architectures with folding transformations.

Lech Szymanski, Brendan McCane

Proceedings of the 2013 International Joint Conference on Neural Networks, 2013

2012

Deep, super-narrow neural network is a universal classifier.

Lech Szymanski, Brendan McCane

Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), 2012

Push-pull separability objective for supervised layer-wise training of neural networks.

Lech Szymanski, Brendan McCane

Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), 2012

2005

Comb filter decomposition for robust ASR.

Lech Szymanski, Martin Bouchard

Proceedings of the INTERSPEECH 2005, 2005