• 12 min read
Multimodal Models and Computer Vision: A Deep Dive
In this post, we discuss what multimodals are, how they work, and their impact on solving computer vision problems.
Blog
Petru P.
Machine Learning Engineer @ Google
Latest Posts by Petru P.
• 16 min read
What is a Convolutional Neural Network?
In this guide, we discuss what a Convolutional Neural Network (CNN) is, how they work, and discuss various different applications of CNNs in computer vision models.
• 14 min read
Transformer Architecture: What Is a Transformer?
In this guide, we explore what Transformers are, why Transformers are so important in computer vision, and how they work.
• 10 min read
What is an Activation Function? A Complete Guide.
In this article, we discuss what an activation function is, why they are used, and what types of activation functions are commonly used.
• 9 min read
What Is Zero Shot Learning in Computer Vision?
In this article, we discuss what zero-shot learning is, how it works, and when zero-shot learning is and is not useful.
• 7 min read
What is Semi-Supervised Learning? A Guide for Beginners.
In this post, we discuss what semi-supervised learning is and walk through the techniques used in semi-supervised learning.
• 8 min read
What is an Autoencoder?
SUMMARY
An autoencoder is a neural network that compresses an input into a compact latent vector and then reconstructs it, with the latent representation, not the output, being the useful artifact. Six main variants exist for computer vision: undercomplete, denoising, sparse, contrastive, Variational (VAE), and Vector Quantised-Variational (VQ-VAE)
• 9 min read
Supervised Learning vs. Unsupervised Learning: Explained
Learn what supervised and unsupervised learning are and how they compare.
Stay Connected