Learn More
Protein-protein interactions play a key role in many biological systems. High-throughput methods can directly detect the set of interacting proteins in yeast, but the results are often incomplete and exhibit high false-positive and false-negative rates. Recently, many different research groups independently suggested using supervised learning methods to(More)
In this article we present Supervised Semantic Indexing (SSI) which defines a class of nonlinear (quadratic) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score. Like Latent Semantic Indexing (LSI), our models take account of correlations between words (synonymy,(More)
Human immunodeficiency virus-1 (HIV-1) in acquired immune deficiency syndrome (AIDS) relies on human host cell proteins in virtually every aspect of its life cycle. Knowledge of the set of interacting human and viral proteins would greatly contribute to our understanding of the mechanisms of infection and subsequently to the design of new therapeutic(More)
Latent semantic analysis (LSA), as one of the most popular unsupervised dimension reduction tools, has a wide range of applications in text mining and information retrieval. The key idea of LSA is to learn a projection matrix that maps the high dimensional vector space representations of documents to a lower dimensional latent space, i.e. so called latent(More)
We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score. Dealing with polynomial models on word features is computationally challenging. We propose a low-rank (but diagonal preserving) representation of our polynomial models(More)
This paper is organized in three parts. The first part details some of the lower level shot classification work, the second part describes the 'manual' retrieval systems while the last section details the interactive retrieval system for the Carnegie Mellon University TREC Video Retrieval Track runs. The description of the data can be found elsewhere in the(More)
Identifying protein-protein interactions (PPI's) is critical for understanding virtually all cellular molecular mechanisms. Previously, predicting PPI's was treated as a binary classification task and has commonly been solved in a supervised setting which requires a positive labeled set of known PPI's and a negative labeled set of non-interacting protein(More)
In this paper we introduce a deep neural network architecture to perform information extraction on character-based sequences, e.g. named-entity recognition on Chinese text or secondary-structure detection on protein sequences. With a task-independent architecture, the deep network relies only on simple character-based features, which obviates the need for(More)
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework is that it connects the sparse-encoders from different layers by a sparse-to-dense module. The sparse-to-dense module(More)
Nonparametric methods have become increasingly popular in statistics and probabilistic AI communities. One well-known nonparametric method is " nearest-neighbor ". It uses the observations in the training set T closest in input space to a query q to form the prediction of q. Specifically, when k of the observations in T are considered, it is called(More)