Applied Machine Learning, Part 4: Embedded Systems
From the series: Applied Machine Learning
Walk through several key techniques and best practices for running your machine learning model on embedded devices.
The video discusses options for making your model faster and reducing its memory footprint, including automatic C/C++ code generation, feature selection, and model reduction.
Published: 18 Jan 2019
The phrase “machine learning” brings to mind complex algorithms that use lots of computations to train a model. But computations on “embedded devices” are limited in the amount of memory and compute available.
Now, when I say “embedded devices,” I’m referring to objects with a special-purpose computing system, so think of things like a household appliance or sensors in an autonomous vehicle.
Today, we’ll discuss the different factors to keep in mind when preparing your machine learning model for an embedded device.
Different types of models require different amounts of memory and time in order to make a prediction. For example, single decision trees are fast and require a small amount of memory. Nearest neighbor methods are slower and require more memory, so you might not want to use them for embedded applications.
Another thing to keep in mind when determining which models to use on an embedded device is how you will get your model to the device.
Most embedded systems are programmed in low-level languages such as C.
But machine learning is typically done in high-level interpreted languages such as MATLAB, Python, or R.
If you have to maintain code bases in 2 different languages, it is going to be very painful to keep them in sync.
MATLAB provides tools that automatically convert a machine learning model to C code, so you don’t need to manually implement the model in C separately.
So what if, after converting a model to C, you find out that it isn’t going to meet the requirements of our system? Maybe the memory footprint is too big, or the model takes too long to make predictions?
You could try other types of models and see if the code meets the requirements. Maybe start with a simple model such as a decision tree.
Alternatively, you could go back earlier in the process and see if you can reduce the number of features in the model. You can use tools such as neighborhood component analysis, which are useful for determining the impact that the features have on the results. If you see that some features are weighted low, you could drop them from our model, making our model more concise.
Certain types of models have different reduction techniques associated with them. For decision trees, you can use pruning techniques, where you drop nodes that provide the smallest accuracy improvement.
One other approach is to look at reducing the memory required for storing the model parameters. For example, seeing if the model can be converted to a fixed-point representation that maintains acceptable accuracy.
Depending on your use case, any of these tactics may be appropriate. Hardware considerations, network connections, and budget are all key factors that will influence design decisions.
That was just a quick overview of embedding machine learning models. For more information on preparing models for embedded devices, see the links below.
Related Videos:
웹사이트 선택
번역된 콘텐츠를 보고 지역별 이벤트와 혜택을 살펴보려면 웹사이트를 선택하십시오. 현재 계신 지역에 따라 다음 웹사이트를 권장합니다:
또한 다음 목록에서 웹사이트를 선택하실 수도 있습니다.
사이트 성능 최적화 방법
최고의 사이트 성능을 위해 중국 사이트(중국어 또는 영어)를 선택하십시오. 현재 계신 지역에서는 다른 국가의 MathWorks 사이트 방문이 최적화되지 않았습니다.
미주
- América Latina (Español)
- Canada (English)
- United States (English)
유럽
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)
아시아 태평양
- Australia (English)
- India (English)
- New Zealand (English)
- 中国
- 日本Japanese (日本語)
- 한국Korean (한국어)