Alex Sergeev
Alex Sergeev is a deep learning engineer on the Machine Learning Platform team.
Engineering Blog Articles
Faster Neural Networks Straight from JPEG
Uber AI Labs introduces a method for making neural networks that process images faster and more accurately by leveraging JPEG representations.
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
As powerful and widespread as convolutional neural networks are in deep learning, AI Labs’ latest research reveals both an underappreciated failing and a simple fix.
Meet Horovod: Uber’s Open Source Distributed Deep Learning Framework for TensorFlow
Uber Engineering introduces Horovod, an open source framework that makes it faster and easier to train deep learning models with TensorFlow.
Research Papers
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
R. Liu, J. Lehman, P. Molino, F.i Such, E. Frank, A. Sergeev, J. Yosinski
Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional neural networks may be appropriate. In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x,y) Cartesian space and one-hot pixel space. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2018
Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional neural networks may be appropriate. In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x,y) Cartesian space and one-hot pixel space. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2018
Faster Neural Networks Straight from JPEG
L. Gueguen, A. Sergeev, B. Kadlec, R. Liu, J. Yosinski
The simple, elegant approach of training convolutional neural networks (CNNs) directly from RGB pixels has enjoyed overwhelming empirical success. But can more performance be squeezed out of networks by using different input representations? In this paper we propose and explore a simple idea: train CNNs directly on the blockwise discrete cosine transform (DCT) coefficients computed and available in the middle of the JPEG codec. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2018
The simple, elegant approach of training convolutional neural networks (CNNs) directly from RGB pixels has enjoyed overwhelming empirical success. But can more performance be squeezed out of networks by using different input representations? In this paper we propose and explore a simple idea: train CNNs directly on the blockwise discrete cosine transform (DCT) coefficients computed and available in the middle of the JPEG codec. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2018
