Credit points: 3.0
Course name (subtitle): “System Aspects of machine learning”
Target: Efficient implementation of machine learning in general and convolutional networks in particular requires a good understanding of the entire systems; e.g., SW environment to support the development process, hardware capabilities and limitations, optimization techniques and more.
Understanding each of these aspects by itself is not sufficient anymore and an architectural view of the entire system is required in order to educate the student to deal with the challenges of current and future challenges
In this course we will learn how to program machine learning algorithms on CPU, GPU and FPGA and how to optimize them for best performance and power
Grad: 60% homework
40% final work/exam
Course name (subtitle): “System Aspects of machine learning”
Target: Efficient implementation of machine learning in general and convolutional networks in particular requires a good understanding of the entire systems; e.g., SW environment to support the development process, hardware capabilities and limitations, optimization techniques and more.
Understanding each of these aspects by itself is not sufficient anymore and an architectural view of the entire system is required in order to educate the student to deal with the challenges of current and future challenges
In this course we will learn how to program machine learning algorithms on CPU, GPU and FPGA and how to optimize them for best performance and power
Grad: 60% homework
40% final work/exam