Advancing the state of the art

Learning to Rank, a central problem in information retrieval, is a class of machine learning algorithms that formulate ranking as an optimization task. The objective is to learn a function that produces an ordering of a set of objects in such a way that the utility of the entire ordered list is maximized. Learning-to-rank methods do so by constructing a function that computes a score for each...

In this paper, we address the problem of learning to perform sequential OCR on photos of street name signs in a language for which no labeled data exists. Our approach leverages easily-generated synthetic data and existing labeled data in other languages to achieve reasonable performance on these unlabeled images, through a combination of a novel domain adaptation technique based on gradient...

Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time dimension, using modules such as 3D convolutions, or by using two-stream design to capture both appearance and motion in videos. We interpret a video CNN as a...

We discuss technology options and challenges for beyond 1Tb/s intra-datacenter interconnect bandwidth scaling, with a focus on pulse amplitude modulation (PAM)-based intensity modulation-direct detection (IM-DD) and baud-rate digital signal processing (DSP)-based coherent technology. We show that a flexible PAM (FlexPAM) technique with fine granularity of bandwidth/spectral efficiency (in terms...

Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently genetic algorithms and other stochastic methods. These methods suffer from frequent costly hardware measurements...

Humans do not acquire perceptual abilities like we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies far greater on multimodal unsupervised learning (as infants) and active learning (as children). With this motivation, we present a learning framework for sound representation and...

Quantum algorithms offer a dramatic speedup for computational problems in machine learning, material science, and chemistry. However, any near-term realizations of these algorithms will need to be heavily optimized to fit within the finite resources offered by existing noisy quantum hardware. Here, taking advantage of the strong adjustable coupling of gmon qubits, we demonstrate a continuous...