Udemy – Deep Learning on ARM Processors – From Ground Up™ 2020-9 – Download

explanation

Deep Learning on ARM Processors – From the Ground Up, course name, Deep Learning with Processors, ARM Industry. During this time, we went on a fun journey together to see how deep neural network foundations work in microcontroller builds. The work begins by learning the fundamentals of deep learning through code, showing that it is practical and that all the blocks in the builder base that led to building a neural network are large-scale. All of this is education and reasoning about microcontrollers. During this period, we also taught beneficial use of libraries such as Keras and Tensorflow in terms of popular libraries for deep learning for microcontrollers such as CMSIS-NN, CubeMX.AI and TensorFlow Lite.

Deep Learning on ARM Processors – From the Basics What you will learn:

Building a neural network from base without using library uploads
Methodologically, master quantization upload for neural network scaling on microcontrollers.
Build firmware for Human Activity Recognition (HAR) diagnostics such as walking, jogging, etc.
Building firmware deep learning for handwriting recognition
Building firmware deep learning for Acoustic Scene Classification (ASC)
We can talk about what deep learning gives us.

Specification Volume:

Publisher: Udemy
teacher: Israel Gbathi and EmbeddedExpertIO
Language:English
Training level: Basic to advanced
Number of courses: 118
Duration: 19 hours 16 minutes

Course content:

1. Introduction
2. Components of a neural network
3. Introduction to Neural Networks (Part 2)
4. Logistic regression
5. Deep neural network
6. Neural network improvement through regularization technology
7. Building a logistic regression model
8. Building a deep neural network from scratch
9. Convolutional Neural Network (CNN)
10. CubeMX 5 and CubeIDE Primer
11. CubeMX AI
12. Case study of MNIST handwriting recognition model deployment on ARM MCU
13. Settings
14. Python Essentials
15. CubeMX Primer
16. Closing