Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this limitation by reducing the memory footprint, latency, or energy consumption of a model with minimal impact on accuracy. We focus on the task of reducing the number of learnable variables in the model. In this work we combine ideas from weight hashing and dimensionality reductions resulting in a simple and powerful structured multi-hashing method based on matrix products that allows direct control of model size of any deep network and is trained end-to-end. We demonstrate the strength of our approach by compressing models from the ResNet, EfficientNet, and MobileNet architecture families. Our method allows us to drastically decrease the number of variables while maintaining high accuracy. For instance, by applying our approach to EfficentNet-B4 (16M parameters) we reduce it to the size of B0 (5M parameters), while gaining over 3% in accuracy over B0 baseline. On the commonly used benchmark CIFAR10 we reduce the ResNet32 model by 75% with no loss in quality, and are able to do a 10x compression while still achieving above 90% accuracy.

Visualization has proved an efficient tool in the understanding of large data sets in computational science and engineering. There is growing interest today in the development of problem solving environments which integrate both visualization and the computational process which generates the data. The GRASPARC project has looked at some of the issues involved in creating such an environment. An architecture is proposed in which tools for computation and visualization can be embedded in a framework which assists in the management of the problem solving process. This framework has an integral data management facility which allows an audit trail of the experiments to be recorded. This design therefore allows not only steering but also backtracking and more complicated problem solving strategies. A number of demonstrator case studies have been implemented.>