Blog: Neural Networks

Backpropagation is a fundamental component of deep learning for neural networks. Its development has significantly contributed to the widespread adoption of deep learning algorithms since the early 2000s. In this post, we explore the essential concepts associated with this method, as well as its applications and history.

Stable Diffusion is a free, open-source neural network for generating photorealistic and artistic images based on text-to-image and image-to-image diffusion models. Read our tips to start generating your own masterpieces in minutes.

Find out how the one-shot learning algorithm works and the practical applications of this novel paradigm in neural networks.

What are the best strategies for training neural networks? How to avoid overfitting? Which open-source datasets to choose? Find the answers to these questions in our interview with Dr. Varun Ojha.

Deep learning has been a game changer in the field of computer vision. It’s widely used to teach computers to “see” and analyze the environment similarly to the way humans do.

What does it take to build a model with 12 billion parameters? Why is open-source culture important in machine learning research? Find out the answers to these questions in our interview with Sergei Markov, the chief of the SberDevices experimental machine learning systems department.

Self-supervised learning is one of the most popular approaches to ML today. SSL algorithms don’t require manual target labeling and can obtain all the information they need from the data. Find out more about how they work in our new post.

This beginner guide will help you understand how convolution neural networks (CNNs) work and what they are useful for.

The difference between deep learning and neural networks is often confusing for beginners. What does it mean for an algorithm to be “deep”? What types of neural networks exist out there? You’ll learn all that and more in our guide.