VTC Academy | Visual Understanding
Visual Understanding
Course format: On campus
Duration: 16 weeks
Major: Artificial Intelligence
ENROLL NOWIntroduction
The Visual Understanding Course for AI Specialist provides top Deep Learning architectures, techniques, models, and algorithms for Visual Understanding, Visual Understanding Environment.
As a result, students are able to build Deep Learning models and AI applications relating to Visual Understanding.
Applicable areas of course
Who can learn?
GROUP 1: People who know about python programming, linear algebra, analytics, optimization * People who have logical thinking and critical thinking *
GROUP 2: Students who have been awarded AI Practitioner certificates by VTC Academy
* Subject to the International-standards-based competency assessment of VTC Academy
Course overview
- Excellent Deep Learning architecture, models and algorithms for Visual understanding (computer vision operations, multimodal data, reasoning capacities)
- Various Deep Learning models for Computer vision: Vgg, Inception, u-Net/CheXNet/MrNet, resNet, DenseNet, yoLo MobileNet, shuffleNet, EffNet, etc.
- Deep Learning techniques: generative Adversarial Networks (gANs), Variational Autoencoder (VAE), meta/transfer/few-shot learning, evolutionary search, Bayesopt, DeeprL, etc.
- Topics of Visual Understanding: Image, object, scene, Video, Behavior, 3D, setting, Integration, etc.
- Step-by-step development of Deep Learning models and AI applications
Course outcomes
Testimonials
