In this project we explore different ways in which we can optimize the computation of training a Tree-structured RNTN, in particular batching techniques in combining many matrix-vector multiplications into matrix-matrix multiplications, and many tensor-vector operations into tensor-matrix operations. We assume that training is performed using mini-batch AdaGrad algorithm, and explore how we can...

We present Tree, a new approach to structural classification. This integrated approach induces decision trees that test for pattern occurrence in the inner nodes. It combines state-of-the-art tree mining with sophisticated pruning techniques to find the most discriminative pattern in each node. In contrast to existing methods, Tree uses no heuristics and only a single, statistically well founde...

Textual Inference is a research trend in Natural Language Processing (NLP) that has recently received a lot of attention by the scientific community. Textual Entailment (TE) is a specific task in Textual Inference that aims at determining whether a hypothesis is entailed by a text. Usually tackled by machine learning techniques employing features which represent similarity between texts, the re...

We describe a framework for defining the space of organization designs for computational agents, use our framework for analyzing the expected performance of a class of organizations, and describe how our analyses can be applied to predict performance for a distributed information gathering task. Our analysis specifically addresses the impact of the span of control (branching factor) in tree-str...

Sequential LSTM has been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of input word information only for leaf nodes. This is different from sequential LSTMs, which contain reference to input words for each node. In this paper, we propose a method for...

Title of Dissertation: CLASSIFICATION AND COMPRESSION OF MULTIRESOLUTION VECTORS: A TREE STRUCTURED VECTOR QUANTIZER APPROACH Sudhir Varma, Doctor of Philosophy, 2002 Dissertation directed by: Professor John S. Baras Department of Electrical and Computer Engineering Tree structured classifiers and quantizers have been used with good success for problems ranging from successive refinement coding...

When analyzing high-dimensional data with many elements, a visualization that maps the onto low-dimensional space is often performed. By visualizing data, humans can intuitively understand structure of in space. The self-organizing map (SOM) one such method. We propose spherical tree-structured SOM (S-TS-SOM), which speeds up search for winner nodes and eliminates unevenness learning due to pos...

In computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving problems using traditional convolutional neural networks. To improve the accuracy and training time of networks problems, this paper proposes a tree-structured framework by eliminating effect dif...

Constrained storage vector quantization, (CSVQ), introduced by Chan and Gersho (1990, 1991) allows for the stagewise design of balanced tree-structured residual vector quantization codebooks with low encoding and storage complexities. On the other hand, it has been established by Makhoul et al. (1985), Riskin et al. (1991), and by Mahesh et al. (see IEEE Trans. Inform. Theory, vol.41, p.917-30,...