Get in Touch
 Duration 14 hours

Course Outline

Introduction to Edge AI and the Ascend 310

  • Edge AI landscape: trends, limitations, and key applications
  • Architecture of the Huawei Ascend 310 chip and its supported toolchain
  • The role of CANN within the edge AI deployment stack

Model Preparation and Conversion

  • Exporting trained models from TensorFlow, PyTorch, and MindSpore
  • Utilising ATC to transform models into OM format for Ascend hardware
  • Addressing unsupported operations and employing lightweight conversion tactics

Building Inference Pipelines with AscendCL

  • Executing OM models on the Ascend 310 via the AscendCL API
  • Handling input/output preprocessing, memory management, and device control
  • Deployment within embedded containers or lightweight runtime settings

Optimising for Edge Constraints

  • Minimising model size and adjusting precision (FP16, INT8)
  • Leveraging the CANN profiler to detect performance bottlenecks
  • Managing memory layout and data streaming to enhance performance

Deployment with MindSpore Lite

  • Utilising the MindSpore Lite runtime for mobile and embedded platforms
  • Comparing MindSpore Lite against raw AscendCL pipelines
  • Packaging inference models for device-specific rollouts

Edge Deployment Scenarios and Case Studies

  • Case study: Smart camera with an object detection model on Ascend 310
  • Case study: Real-time classification in an IoT sensor hub
  • Monitoring and updating models deployed at the edge

Summary and Next Steps

Requirements

  • Practical experience in AI model development or deployment processes
  • Foundational understanding of embedded systems, Linux, and Python
  • Familiarity with deep learning frameworks like TensorFlow or PyTorch

Target Audience

  • IoT solution developers
  • Embedded AI engineers
  • Edge system integrators and AI deployment specialists

Number of participants


Price per participant

Open Training Courses require 5+ participants.

Testimonials (1)

That we can cover advance topic and work with real-life example

Ruben Khachaturyan - iris-GmbH infrared & intelligent sensors
Course - Advanced Edge AI Techniques

Upcoming Courses

CANN for Edge AI Deployment

2026-11-24 09:30
14 hours
Naples
2100 EUR (Online)
2500 EUR (Classroom)

CANN for Edge AI Deployment

2026-12-08 09:30
14 hours
Turin
2100 EUR (Online)
2500 EUR (Classroom)

CANN for Edge AI Deployment

2026-12-22 09:30
14 hours
Genoa
2100 EUR (Online)
2500 EUR (Classroom)

CANN for Edge AI Deployment

2027-01-05 09:30
14 hours
Bologna
2100 EUR (Online)
2500 EUR (Classroom)

Related Courses

5G and Edge AI: Enabling Ultra-Low Latency Applications

 21 Hours

This instructor-led, live training in Italy (online or onsite) is designed for intermediate-level telecom professionals, AI engineers, and IoT specialists eager to explore how 5G networks enhance Edge AI applications.

By the end of this training, participants will be able to:

  • Grasp the fundamentals of 5G technology and its influence on Edge AI.
  • Deploy AI models tailored for low-latency applications within 5G environments.
  • Implement real-time decision-making systems leveraging Edge AI and 5G connectivity.
  • Optimize AI workloads to ensure efficient performance on edge devices.
Read more...

6G and the Intelligent Edge

 21 Hours

This 21-hour training in Italy guides IT architects in designing next-gen distributed systems. Explore 6G, edge computing, and AI integration for low-latency, scalable infrastructures. Gain practical skills for secure, resilient, and intelligent edge architectures to meet future business demands.

Read more...

Advanced Edge AI Techniques

 14 Hours

This instructor-led, live training in Italy (online or onsite) is aimed at advanced-level AI practitioners, researchers, and developers who wish to master the latest advancements in Edge AI, optimize their AI models for edge deployment, and explore specialized applications across various industries.

By the end of this training, participants will be able to:

  • Explore advanced techniques in Edge AI model development and optimization.
  • Implement cutting-edge strategies for deploying AI models on edge devices.
  • Utilize specialized tools and frameworks for advanced Edge AI applications.
  • Optimize performance and efficiency of Edge AI solutions.
  • Explore innovative use cases and emerging trends in Edge AI.
  • Address advanced ethical and security considerations in Edge AI deployments.
Read more...

Developing AI Applications with Huawei Ascend and CANN

 21 Hours
This instructor-led course on Italy helps intermediate AI engineers construct and refine neural network models using the Huawei Ascend platform and CANN toolkit. Learners will set up environments, develop applications with MindSpore, and deploy solutions to edge or cloud contexts.
Read more...

Deploying AI Models with CANN and Ascend AI Processors

 14 Hours
This live training in Italy supports intermediate AI developers in deploying models on Ascend processors through the CANN toolkit. Participants will learn to convert frameworks like PyTorch and TensorFlow, optimize performance, and resolve issues for efficient edge and cloud inference.
Read more...

Building AI Solutions on the Edge

 14 Hours

This live, instructor-led training in Italy (delivered online or onsite) is tailored for intermediate developers, data scientists, and tech enthusiasts seeking to acquire practical expertise in deploying AI models on edge devices for diverse applications.

By the conclusion of this program, participants will be able to:

  • Comprehend the fundamentals of Edge AI and its key benefits.
  • Configure and set up an edge computing environment.
  • Design, train, and optimize AI models for edge deployment.
  • Execute practical AI solutions on edge hardware.
  • Monitor and improve the performance of edge-deployed models.
  • Manage ethical and security aspects within Edge AI applications.
Read more...

Building Secure and Resilient Edge AI Systems

 21 Hours

This instructor-led, live training in Italy (online or onsite) is designed for advanced cybersecurity professionals, AI engineers, and IoT developers seeking to implement robust security measures and resilience strategies for Edge AI systems.

Upon completion of this training, participants will be able to:

  • Comprehend the security risks and vulnerabilities associated with Edge AI deployments.
  • Apply encryption and authentication techniques to protect data.
  • Architect resilient Edge AI systems capable of withstanding cyber threats.
  • Execute secure AI model deployment strategies within edge environments.
Read more...

Cambricon MLU Development with BANGPy and Neuware

 21 Hours
This live, instructor-led training in Italy empowers developers with the expertise required to build and deploy AI models using BANGPy and Neuware on Cambricon MLUs. Participants will learn to configure environments, develop optimized models, and integrate MLU acceleration into edge and data center applications.
Read more...

Introduction to CANN for AI Framework Developers

 7 Hours
This live training in Italy provides an introduction to the CANN toolkit for AI framework developers. Participants will learn how to configure environments, convert models, and deploy applications on Ascend hardware using MindSpore, TensorFlow, or PyTorch, covering the complete workflow from training to inference.
Read more...

Understanding Huawei’s AI Compute Stack: From CANN to MindSpore

 14 Hours
This live, instructor-led training in Italy delves into Huawei's AI ecosystem, ranging from the CANN SDK to the MindSpore framework. It assists entry-level and intermediate professionals in comprehending how these components converge on Ascend hardware to optimize lifecycle management and deployment.
Read more...

Optimizing Neural Network Performance with CANN SDK

 14 Hours
Enhance neural network inference performance on Ascend AI processors through this advanced, instructor-led training in Italy. Gain insight into CANN's runtime architecture, utilizing the Graph Engine, TIK, and TVM for profiling, custom operator development, and resolving memory bottlenecks.
Read more...

CANN SDK for Computer Vision and NLP Pipelines

 14 Hours
This instructor-led training on Italy focuses on deploying and optimizing CV and NLP models using the CANN SDK for Ascend hardware. Participants will learn to convert models, integrate them into live pipelines, and enhance inference performance for real-time detection and analysis.
Read more...

Building Custom AI Operators with CANN TIK and TVM

 14 Hours
This live, instructor-led training in Italy empowers advanced developers with the capabilities to design, deploy, and fine-tune custom AI operators. Learners will gain mastery over CANN TIK and Apache TVM integration, facilitating high-level optimization and scheduling on Huawei Ascend hardware for tangible real-world performance gains.
Read more...

Applied Edge AI

 35 Hours

Combine the transformative power of AI with the agility of edge computing in this comprehensive course. Learn to deploy AI models directly on edge devices, from understanding CNN architectures to mastering knowledge distillation and federated learning. This hands-on training will equip you with the skills to optimize AI performance for real-time processing and decision-making at the edge.

Read more...

Edge AI for Agriculture: Smart Farming and Precision Monitoring

 21 Hours

This instructor-led, live training in Italy (online or onsite) is designed for beginner to intermediate-level agritech professionals, IoT specialists, and AI engineers looking to develop and deploy Edge AI solutions for smart farming.

By the end of this training, participants will be able to:

  • Understand the role of Edge AI in precision agriculture.
  • Implement AI-driven crop and livestock monitoring systems.
  • Develop automated irrigation and environmental sensing solutions.
  • Optimize agricultural efficiency using real-time Edge AI analytics.
Read more...

Related Categories

Edge AI
Edge AI
CANN
CANN