Search Results for author:
Found 9 papers, 4 papers with code
Evolving GAN Formulations for Higher Quality Image Synthesis
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities.
Effective Regularization Through Loss-Function Metalearning
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.
Pan-Cancer Computational Histopathology (PC-CHiP) analysis using deep learning
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.
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes.
Regularized Evolutionary Population-Based Training
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.
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research.
Improved Training Speed, Accuracy, and Data Utilization via Loss Function Optimization
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
Ranked #44 on
Image Classification
on MNIST
Faster Training by Selecting Samples Using Embeddings
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.
