Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the structured perceptron can be costly to train as training complexity is proportional to inference, which is frequently non-linear in example sequence length. In this paper we investigate distributed training strategies ...

As the number of pipeline stages increases we become hostage to the penalty imposed by misprediction of branches. Previous works have shown that a neural branch predictor remains victorious among its peers by achieving much lower misprediction rates on similar sized hardware budget than traditional approaches. In this paper we implement 3 variations of perceptron based predictor and give each i...

We present our experiments applying, off-the-shelf, two existing Named Entity Recognition (NER) taggers for the Biomedical Abbreviation Recognition and Resolution (BARR) task at IberEval 2017. The first system is a Perceptron tagger based on sparse, shallow features whereas the second is a bidirectional Long-Short Term Memory neural network with a sequential conditional random layer above it (L...

Reliable results are crucial when working with medical decision support systems. A decision support system should be reliable but also be interpretable, i.e. able to show how it has inferred its conclusions. In this thesis, the preprocessing perceptron is presented as a simple but effective and efficient analysis method to consider when creating medical decision support systems. The preprocessi...

The perceptron branch predictor has been recently proposed by Jiménez and Lin as an alternative to conventional branch predictors. In this paper, we build upon this original proposal in three directions. First, we show that the potential accuracy that can be achieved by perceptron-like predictors was largely underestimated. The accuracy of the redundant history skewed perceptron predictor (RHSP...

Boolean satisfiability (SAT) as a canonical NP-complete decision problem is one of the most important problems in computer science. In practice, real-world SAT sentences are drawn from a distribution that may result in efficient algorithms for their solution. Such SAT instances are likely to have shared characteristics and substructures. This work approaches the exploration of a family of SAT s...

A new learning method, the fuzzy kernel perceptron (FKP), in which the fuzzy perceptron (FP) and the Mercer kernels are incorporated, is proposed in this paper. The proposed method first maps the input data into a high-dimensional feature space using some implicit mapping functions. Then, the FP is adopted to find a linear separating hyperplane in the high-dimensional feature space. Compared wi...

In this paper, we show that a kernel-based perceptron can be efficiently implemented in digital hardware using very few components. Despite its simplicity, the experimental results on standard data sets show remarkable performance in terms of generalization error. Introduction: A practical way to build non-linear