no code implementations • 17 Feb 2021 • Santiago Gonzalez, Mohak Kant, Risto Miikkulainen
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities.
no code implementations • 2 Oct 2020 • Santiago Gonzalez, Risto Miikkulainen
Evolutionary optimization, such as the TaylorGLO method, can be used to discover novel, customized loss functions for deep neural networks, resulting in improved performance, faster training, and improved data utilization.
1 code implementation • 27 Jul 2020 • Yu Fu, Alexander W Jung, Ramon Viñas Torne, Santiago Gonzalez, Harald Vöhringer, Artem Shmatko, Lucy Yates, Mercedes Jimenez-Linan, Luiza Moore, Moritz Gerstung
These findings demonstrate the large potential of computer vision to characterise the molecular basis of tumour histopathology and lay out a rationale for integrating molecular and histopathological data to augment diagnostic and prognostic workflows.
1 code implementation • 13 Feb 2020 • Olivier Francon, Santiago Gonzalez, Babak Hodjat, Elliot Meyerson, Risto Miikkulainen, Xin Qiu, Hormoz Shahrzad
Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes.
no code implementations • 11 Feb 2020 • Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, Risto Miikkulainen
This paper presents an algorithm called Evolutionary Population-Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions.
1 code implementation • 31 Jan 2020 • Santiago Gonzalez, Risto Miikkulainen
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research.
no code implementations • 25 Sep 2019 • Santiago Gonzalez, Risto Miikkulainen
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
2 code implementations • 27 May 2019 • Santiago Gonzalez, Risto Miikkulainen
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
Ranked #36 on Image Classification on MNIST
no code implementations • 27 Sep 2018 • Santiago Gonzalez, Joshua Landgraf, Risto Miikkulainen
Long training times have increasingly become a burden for researchers by slowing down the pace of innovation, with some models taking days or weeks to train.