Naveen NairAmazon
Naveen Nair
PhD Computer Science And Eng. (Machine Learning)
About
9
Publications
171
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
11
Citations
Introduction
I work on improving machine learning and inductive logic programming algorithms. I would like to contribute to the scientific advancements by inventing new methodologies, products and services. My goal includes publishing in top conferences/journals and/or getting patents.
I am currently working with the Machine Learning team of Amazon. Prior to that, I have completed my PhD from IIT Bombay, India and Monash University, Australia (dual badged PhD programme).
Publications
Publications (9)
The goal in Rule Ensemble Learning (REL) is simultaneous discovery of a small set of simple rules and their optimal weights that lead to good generalization. Rules are assumed to be conjunctions of basic propositions concerning the values taken by the input features. It has been shown that rule ensembles for classification can be learnt optimally a...
Discovering relational structure between input features in sequence labeling models has shown to improve their accuracy in several problem settings. However, the search space of relational features is exponential in the number of basic input features. Consequently, approaches that learn relational features, tend to follow a greedy search strategy....
Building relational models for the structured output classification problem of sequence labeling has been recently explored in a few research works. The models built in such a manner are interpretable and capture much more information about the domain (than models built directly from basic attributes), resulting in accurate predictions. On the othe...
Discovering relational structure between input features in sequence labeling models has shown to improve their accuracies in several problem settings. The problem of learning relational structure for sequence labeling can be posed as learning Markov Logic Networks (MLN) for sequence labeling, which we abbreviate as Markov Logic Chains (MLC). This o...
Non intrusive activity recognition systems typically read values from sensors deployed in an environment and combine them with user annotated activities to build a probabilistic model. Recently, features constructed from activity specific conjunctions of binary sensor values have been shown to improve the classification accuracy. Such systems emplo...
Hidden Markov Models (HMMs) are widely used in activity recognition. Ideally, the current activity should be determined using
the vector of all sensor readings; however, this results in an exponentially large space of observations. The current fix
to this problem is to assume conditional independence between individual sensors, given an activity, a...
Many SRL models pose logical inference as weighted satisfiability solving. Performing logical inference after completely grounding
clauses with all possible constants is computationally expensive and approaches such as LazySAT [8] utilize the sparseness
of the domain to deal with this. Here, we investigate the efficiency of restricting the Knowledg...