Ron Weiss

Bio: Ron Weiss is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Synthetic biology & Speech synthesis. The author has an hindex of 82, co-authored 292 publications receiving 89189 citations. Previous affiliations of Ron Weiss include French Institute for Research in Computer Science and Automation & Google.

Factored spatial and spectral multichannel raw waveform CLDNNs

Abstract: Multichannel ASR systems commonly separate speech enhancement, including localization, beamforming and postfiltering, from acoustic modeling. Recently, we explored doing multichannel enhancement jointly with acoustic modeling, where beamforming and frequency decomposition was folded into one layer of the neural network [1, 2]. In this paper, we explore factoring these operations into separate layers in the network. Furthermore, we explore using multi-task learning (MTL) as a proxy for postfiltering, where we train the network to predict "clean" features as well as context-dependent states. We find that with the factored architecture, we can achieve a 10% relative improvement in WER over a single channel and a 5% relative improvement over the unfactored model from [1] on a 2,000-hour Voice Search task. In addition, by incorporating MTL, we can achieve 11% and 7% relative improvements over single channel and unfactored multichannel models, respectively.

Latent Collaborative Retrieval

Abstract: Retrieval tasks typically require a ranking of items given a query. Collaborative filtering tasks, on the other hand, learn to model user's preferences over items. In this paper we study the joint problem of recommending items to a user with respect to a given query, which is a surprisingly common task. This setup differs from the standard collaborative filtering one in that we are given a query × user × item tensor for training instead of the more traditional user × item matrix. Compared to document retrieval we do have a query, but we may or may not have content features (we will consider both cases) and we can also take account of the user's profile. We introduce a factorized model for this new task that optimizes the top-ranked items returned for the given query and user. We report empirical results where it outperforms several baselines.

Processing multi-channel audio waveforms

Abstract: Methods, including computer programs encoded on a computer storage medium, for enhancing the processing of audio waveforms for speech recognition using various neural network processing techniques. In one aspect, a method includes: receiving multiple channels of audio data corresponding to an utterance; convolving each of multiple filters, in a time domain, with each of the multiple channels of audio waveform data to generate convolution outputs, wherein the multiple filters have parameters that have been learned during a training process that jointly trains the multiple filters and trains a deep neural network as an acoustic model; combining, for each of the multiple filters, the convolution outputs for the filter for the multiple channels of audio waveform data; inputting the combined convolution outputs to the deep neural network trained jointly with the multiple filters; and providing a transcription for the utterance that is determined.

A novel Bxb1 integrase RMCE system for high fidelity site-specific integration of mAb expression cassette in CHO Cells.

Abstract: As CHO cell line development for biotherapeutic production becomes more sophisticated through the availability of the CHO genome sequence, the ability to accurately and reproducibly engineer the host cell genome has become increasingly important. Multiple well characterized systems for site-specific integration will enable more complex cell line engineering to generate cell lines with desirable attributes. We built and characterized a novel recombinase mediated cassette exchange (RMCE) system using Bxb1 integrase and compared it to the commonly used Flp/FRT RMCE system. We first integrated a DNA construct flanked by either Bxb1 attachment sites or FRT sequences (referred to as a landing pad) into the Fer1L4 genomic locus of CHO-S cells using CRISPR/Cas9 mediated homologous recombination. We characterized the resulting clones harboring either the Bxb1 or Flp/FRT landing pad using whole genome resequencing to compare their genomes with the parental host cell line. We determined that each landing pad was specifically integrated into the Fer1L4 locus in the selected clones and observed no major structural changes in the genome or variations in copy number as a result of CRISPR/Cas9 modification. We subsequently tested the ability of the Bxb1 and Flp/FRT landing pad clones to perform proper RMCE with donor vectors containing identical mAb expression cassettes flanked by either Bxb1 attachment sites or FRT sites. We demonstrated that both RMCE systems were able to generate stable pools in a similar time frame with comparable mAb expression. Through genetic characterization of up to 24 clones derived from either system, we determined that the BxB1 RMCE system yielded higher fidelity RMCE events than the Flp/FRT system as evidenced by a higher percentage of clones with expected integration of the mAb cassette into the landing pad in the respective cell lines. We conclude that Bxb1 RMCE is an excellent alternative to Flp/FRT RMCE and valuable addition to our toolbox enabling the engineering of more sophisticated cell lines for biotherapeutic production. Biotechnol. Bioeng. 2017;114: 1837-1846. © 2017 Wiley Periodicals, Inc.

Nonlinear latent factorization by embedding multiple user interests

Abstract: Classical matrix factorization approaches to collaborative filtering learn a latent vector for each user and each item, and recommendations are scored via the similarity between two such vectors, which are of the same dimension In this work, we are motivated by the intuition that a user is a much more complicated entity than any single item, and cannot be well described by the same representation Hence, the variety of a user's interests could be better captured by a more complex representation We propose to model the user with a richer set of functions, specifically via a set of latent vectors, where each vector captures one of the user's latent interests or tastes The overall recommendation model is then nonlinear where the matching score between a user and a given item is the maximum matching score over each of the user's latent interests with respect to the item's latent representation We describe a simple, general and efficient algorithm for learning such a model, and apply it to large scale, real-world datasets from YouTube and Google Music, where our approach outperforms existing techniques

疟原虫var基因转换速率变化导致抗原变异[英]／Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A

Abstract: 抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1（PfPMP1）与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用，在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员，通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

XGBoost: A Scalable Tree Boosting System

Abstract: Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.

The anatomy of a large-scale hypertextual Web search engine

Abstract: In this paper, we present Google, a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext. Google is designed to crawl and index the Web efficiently and produce much more satisfying search results than existing systems. The prototype with a full text and hyperlink database of at least 24 million pages is available at http://google.stanford.edu/. To engineer a search engine is a challenging task. Search engines index tens to hundreds of millions of web pages involving a comparable number of distinct terms. They answer tens of millions of queries every day. Despite the importance of large-scale search engines on the web, very little academic research has been done on them. Furthermore, due to rapid advance in technology and web proliferation, creating a web search engine today is very different from three years ago. This paper provides an in-depth description of our large-scale web search engine -- the first such detailed public description we know of to date. Apart from the problems of scaling traditional search techniques to data of this magnitude, there are new technical challenges involved with using the additional information present in hypertext to produce better search results. This paper addresses this question of how to build a practical large-scale system which can exploit the additional information present in hypertext. Also we look at the problem of how to effectively deal with uncontrolled hypertext collections where anyone can publish anything they want.

The PageRank Citation Ranking : Bringing Order to the Web

Abstract: The importance of a Web page is an inherently subjective matter, which depends on the readers interests, knowledge and attitudes. But there is still much that can be said objectively about the relative importance of Web pages. This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them. We compare PageRank to an idealized random Web surfer. We show how to efficiently compute PageRank for large numbers of pages. And, we show how to apply PageRank to search and to user navigation.

XGBoost: A Scalable Tree Boosting System

Abstract: Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.