Generative AI Computer Vision Specialization | Level1
Duration
7.5 Hours
Level
Intermediate Level
Design and Tailor this course
As per your team needs
This course immerses you in the captivating realm of Computer Vision Algorithms, offering participants a thorough exploration of fundamental concepts and techniques. Through a carefully crafted series of modules, students will dive into essential topics such as CNN, image analysis algorithms, object detection, feature extraction, and more. The course covers practical applications, hands-on exercises, and real-world case studies to ensure a well-rounded understanding of Computer Vision. By course completion, participants will have gained the skills and knowledge needed to confidently apply Computer Vision techniques in a variety of contexts.
- Developers and software engineers interested in learning GenerativeAI
- Computer Vision engineers looking to implement GenerativeAI models in various industry use cases.
- AI enthusiasts and professionals aiming to build intelligent and innovative solutions
- Even Data scientists and machine learning practitioners seeking to enhance their skills in working with GenAI models
- Fundamentals of Computer Vision – CNN Overview
- Edge Detection and Padding
- Strided Convolutions and Convolutions Over Volume
- One Layer of a Convolutional Network
- Building a Simple Convolutional Network
- Exploring Pooling Layers
- Deepening Understanding with a CNN
- Overview of Popular image recognition algorithms:
- VGG
- YOLOv3, YOLOv7
- ResNet
- AlexNet
- Understanding GAN
- Approaches for GANs
- CycleGAN
- pix2pix
- Image Reconstruction
- Autoencoders
- Concepts related to Style Transfer
- The Power of Generative AI
- Impact on communication, work, and innovation
- Case study: ChatGPT
- Text Generation
- Overview of text generation techniques: Markov Chains, RNNs, Transformers
- Application: ChatGPT
- Image Generation
- Deep learning algorithms: VAEs, GANs, Stable Diffusion
- Transformer Models in Image Generation.
- Application: MidJourney, DALL-E
- Video and Speech Generation
- Video Generation techniques: GANs, Video Diffusion
- Speech Generation using Transformers
- Application: DeepBrain, Synthesia
Train YOLO Based Object Detection Model
Participants should have attended Foundation for Generative AI course or have an equivalent knowledge.