Maintaining Performance with Less Data
This addresses cost and environmental issues for AI practitioners, but it is incremental as it builds on existing data reduction techniques.
The paper tackles the problem of high computational and environmental costs in deep learning by proposing a method to dynamically reduce input data during training, achieving up to 50% runtime reduction while maintaining accuracy.
We propose a novel method for training a neural network for image classification to reduce input data dynamically, in order to reduce the costs of training a neural network model. As Deep Learning tasks become more popular, their computational complexity increases, leading to more intricate algorithms and models which have longer runtimes and require more input data. The result is a greater cost on time, hardware, and environmental resources. By using data reduction techniques, we reduce the amount of work performed, and therefore the environmental impact of AI techniques, and with dynamic data reduction we show that accuracy may be maintained while reducing runtime by up to 50%, and reducing carbon emission proportionally.