Deep Neural Network Model Development using Machine Learning for a Semiconductor Manufacturer in the US
Overview
The client is a prominent semiconductor manufacturer headquartered in the US, specializing in the production of microcontrollers, processors, sensors, analog integrated circuits (ICs), and connectivity solutions. They wanted a technology partner to help them in proving the application of their newly developed chipsets for Machine Learning at edge to be launched in the market. ACL Digital designed the handwritten digit recognition application using powerful supervised deep learning technique – Convolution Neural Network (CNN) and developed developed Caffe model using AlexNet architecture and trained using MNIST database of 50,000 images with accelerated launch timeline by 30%.
Download Case Study
Challenges
Absence of hand-written digit recognition application on the newly developed chipsets
Solutions
- Designed the handwritten digit recognition application using powerful supervised deep learning technique – Convolution Neural Network (CNN)
- Developed Caffe model using AlexNet architecture and trained using MNIST database of 50,000 images
- Developed script in Python to export model parameter & converted using CMSIS-NN library to deploy on edge – i.MXRT1062
- Developed application in C on NXP i.MXRT1062 for capturing the image, pre-processing and executing deep learning model for digit classification
- Analyzed the performance of the model by tweaking different parameters and layers of the AlexNet architecture
- Performed testing of the model with 10,000+ images
Outcomes
- Accelerated client’s product launch timeline by 30% with hands-on experience in machine learning domain
