Daniel Levy

TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.

TL;DR: This work presents how Convolutional Neural Networks can be used to directly classify pre-segmented breast masses in mammograms as benign or malignant, using a combination of transfer learning, careful pre-processing and data augmentation to overcome limited training data.

TL;DR: The authors derive a connection between input noising in neural network language models and smoothing in $n$-gram models and draw upon ideas from smoothing to develop effective noising schemes.

TL;DR: This work develops a pruning and quantization approach that leverages sparse representations in the underlying cryptosystem to accelerate inference and derives an optimal approximation for popular activation functions that achieves maximally-sparse encodings and minimizes approximation error.

TL;DR: In this article, a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution is presented.