Alex Krizhevsky

scientist · 2 mentions across 2 readings

In this course

Alex Krizhevsky is a computer scientist best known for developing AlexNet, the deep convolutional neural network that won the 2012 ImageNet competition and catalyzed the modern deep learning revolution. The course readings invoke Krizhevsky's work implicitly through discussions of ImageNet benchmarks and the validation metrics used to evaluate generative models, positioning his architectural innovations as foundational to contemporary neural network design and the computational paradigms now central to AI systems.

Mentioned in 2 readings

Andrew Brock

et al., LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS

We compute the IS for both the training and validation sets of ImageNet. At $128 \times 128$ the training data has an IS of 233, and the validation data has an IS of 166. At $256 \times 256$ the training data has an IS of 377, and the valid…

Dan McQuillan

from Resisting AI, an Anti-fascist Approach to Artificial Intelligence

The mathematical power of neural networks comes from their universality: in other words, for any input they can approximate the desired output function. As dry as ‘being able to compute any function’ may sound, it becomes a lot more compell…

Appears alongside

People mentioned in the same passages — sorted by co-occurrence weight.

Alec Radford 1 Geoffrey Hinton 1 Michael Nielsen 1