Modern AI Models for Vision and Multimodal Understanding
Completed by Ehsan Amini
September 17, 2025
12 hours (approximately)
Ehsan Amini's account is verified. Coursera certifies their successful completion of Modern AI Models for Vision and Multimodal Understanding
What you will learn
Apply Nonlinear Support Vector Machines (NSVMs) and Fourier transforms to analyze and process visual data.
Use probabilistic reasoning and implement Recurrent Neural Networks (RNNs) to model temporal sequences and contextual dependencies in visual data.
Explain the principles of transformer architectures and how Vision Transformers (ViT) perform image classification and visual understanding tasks.
Implement CLIP for multimodal learning, and utilize diffusion models to generate high-fidelity images.
Skills you will gain
- Category: Supervised Learning
- Category: Digital Signal Processing
- Category: Embeddings
- Category: Generative Model Architectures
- Category: Transfer Learning
- Category: Vision Transformer (ViT)
- Category: Recurrent Neural Networks (RNNs)
- Category: Classification Algorithms
- Category: Machine Learning Methods
