Data can be represented as a vector in a continuous space, but often it is concentrated in a narrow area. Can it be improved?
DeepNightLearners is a series of summaries in the field of deep learning
Augmenting images training data to add variability doesn't always end well since the augmentation changes the semantic content of the image. Here's how to solve it.
AlphaFold2 is the strongest tool today to predict protein 3D structure. It will be massively used to bring the world protein research forward. Since it is very complex and contains many new architectures, in this post, we gradually decompose the system into its base components.
This paper suggests a new computationally efficient method for constructing low-dimensional representation of unlabeled data.
A review and clear explanation of the NeRF method, which can be used to synthesize 3D scenes out of an input image. This method is the base for many other research methods that followed.