Do you want to learn all the latest state-of-the-art methods of the last year? Learn about the best and most famous papers that made the cut from this year’s ICCV. See the latest trends in AI and computer vision.
This article demystifies the ML learning modeling process under the prism of statistics. We will understand how our assumptions on the data enable us to create meaningful optimization problems.
Explore what is neural architecture search, compare the most popular,SOTA methodologies and implement it with nni
Discorver how to formulate and train Spiking Neural Networks (SNNs) using the LIF model, and how to encode data so that it can be processed by SNNs
Discover what is regularization, why it is necessary in deep neural networks and explore the most frequently used strategies: L1, L2, dropout, stohastic depth, early stopping and more
What is Explainable Artificial Intelligence (XAI), what are the most popular methods, where and how can it be applied
An overview of the most popular optimization algorithms for training deep neural networks. From stohastic gradient descent to Adam, AdaBelief and second-order optimization
How can we efficiently train very deep neural network architectures? What are the best in-layer normalization options? We gathered all you need about normalization in transformers, recurrent neural nets, convolutional neural networks.
What is behind the NALU Deepmind paper
How deep learning is changing the world
How to buld a Convolutional neural network library using C++ and OpenCL
How to buld a neural network library using C++ and OpenCL
Use unsupervised learning to cluster documents based on their content