Generalized Sparse Additive Model google
We present a unified framework for estimation and analysis of generalized additive models in high dimensions. The framework defines a large class of penalized regression estimators, encompassing many existing methods. An efficient computational algorithm for this class is presented that easily scales to thousands of observations and features. We prove minimax optimal convergence bounds for this class under a weak compatibility condition. In addition, we characterize the rate of convergence when this compatibility condition is not met. Finally, we also show that the optimal penalty parameters for structure and sparsity penalties in our framework are linked, allowing cross-validation to be conducted over only a single tuning parameter. We complement our theoretical results with empirical studies comparing some existing methods within this framework. …

Spectral Inference Network google
We present Spectral Inference Networks, a framework for learning eigenfunctions of linear operators by stochastic optimization. Spectral Inference Networks generalize Slow Feature Analysis to generic symmetric operators, and are closely related to Variational Monte Carlo methods from computational physics. As such, they can be a powerful tool for unsupervised representation learning from video or pairs of data. We derive a training algorithm for Spectral Inference Networks that addresses the bias in the gradients due to finite batch size and allows for online learning of multiple eigenfunctions. We show results of training Spectral Inference Networks on problems in quantum mechanics and feature learning for videos on synthetic datasets as well as the Arcade Learning Environment. Our results demonstrate that Spectral Inference Networks accurately recover eigenfunctions of linear operators, can discover interpretable representations from video and find meaningful subgoals in reinforcement learning environments. …

Visual Knowledge Memory Network (VKMN) google
Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can’t be directly or clearly answered from visual content but require reasoning from structured human knowledge with confirmation from visual content. This paper proposes visual knowledge memory network (VKMN) to address this issue, which seamlessly incorporates structured human knowledge and deep visual features into memory networks in an end-to-end learning framework. Comparing to existing methods for leveraging external knowledge for supporting VQA, this paper stresses more on two missing mechanisms. First is the mechanism for integrating visual contents with knowledge facts. VKMN handles this issue by embedding knowledge triples (subject, relation, target) and deep visual features jointly into the visual knowledge features. Second is the mechanism for handling multiple knowledge facts expanding from question and answer pairs. VKMN stores joint embedding using key-value pair structure in the memory networks so that it is easy to handle multiple facts. Experiments show that the proposed method achieves promising results on both VQA v1.0 and v2.0 benchmarks, while outperforms state-of-the-art methods on the knowledge-reasoning related questions. …

Wikipedia WordNet Based QE Technique (WWQE) google
Query expansion (QE) is a well known technique to enhance the effectiveness of information retrieval (IR). QE reformulates the initial query by adding similar terms that helps in retrieving more relevant results. Several approaches have been proposed with remarkable outcome, but they are not evenly favorable for all types of queries. One of the main reasons for this is the use of the same data source while expanding both the individual and the phrase query terms. As a result, the holistic relationship among the query terms is not well captured. To address this issue, we have selected separate data sources for individual and phrase terms. Specifically, we have used WordNet for expanding individual terms and Wikipedia for expanding phrase terms. We have also proposed novel schemes for weighting expanded terms: inlink score (for terms extracted from Wikipedia) and a tfidf based scheme (for terms extracted from WordNet). In the proposed Wikipedia WordNet based QE technique (WWQE), we weigh the expansion terms twice: first, they are scored by the weighting scheme individually, and then, the weighting scheme scores the selected expansion terms in relation to the entire query using correlation score. The experimental results show that the proposed approach successfully combines Wikipedia and WordNet as demonstrated through a better performance on standard evaluation metrics on FIRE dataset. The proposed WWQE approach is also suitable with other standard weighting models for improving the effectiveness of IR. …