Machine Learning Algorithms - Second Edition

GPU support

In the previous two chapters, Chapter 15, Introducing Neural Networks, and Chapter 16, Advanced Deep Learning Models, we have discussed the basic concepts of deep learning models, highlighting how large the number of parameters that characterizes such architectures is. If we consider also the dimensionality of the dataset, it's easy to understand that the computational complexity can become extremely large. Frameworks such as scikit-learn are mainly based on NumPy, which contains highly optimized native code that runs on multi-core CPUs. Moreover, NumPy works with Single Instruction Multiple Data (SIMD) commands and exposes vectorized primitives. This feature, in many cases, allows getting rid of explicit loops, speeding up at ...