Search Results for author:
Found 5 papers, 1 papers with code
On the Non-Associativity of Analog Computations
With this model we assess the importance of ordering by comparing the test accuracy of a neural network for keyword spotting, which is trained based either on an ordered model, on a non-ordered variant, and on real hardware.
Walking Noise: Understanding Implications of Noisy Computations on Classification Tasks
We then investigate the implications of additive and multiplicative noise for different classification tasks and model architectures, with and without batch normalization.
Towards Hardware-Specific Automatic Compression of Neural Networks
Moreover, we can demonstrate that a joint search and compression using pruning and quantization is superior to an individual search for policies using a single compression method.
Understanding Cache Boundness of ML Operators on ARM Processors
Machine Learning compilers like TVM allow a fast and flexible deployment on embedded CPUs.
Resource-Efficient Neural Networks for Embedded Systems
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches.
