The objective of this project is to implement the recursive auto encoder (RAE) method to learn a model to predict sentiments for sentences and reproduce the result in [1]. To learn the weights for recursive functions, we implement forward and backward propagation algorithms. We validate the gradient computed from forward and backward algorithm by comparing it to the gradient computed from numer...

We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, we propose a way to incorporate attention into the tree topology. Specially, given a pair of sentences, our attentive encoder uses the representation of one sen...

We propose a low cost polymeric optical waveguides-based optical CDMA encoder and decoder modules. The structures of the optical CDMA encoder and decoder modules are presented. The performance of the optical CDMA encoder and decoder modules is simulated using 10-chip binary phase-shift keying (BPSK) coding schemes. The optical CDMA encoder and decoder modules can effectively transmit and recove...

This paper addresses a low-cost and real-time solution for the implementation of super-resolution (SR) algorithms over SOC (System-On-Chip) platforms in order to achieve high-quality image improvements. Lowcost constraints are accomplished in the sense that SR is performed without developing a specific hardware, but re-using a video encoder IP block. This encoder can be used either in compressi...

This paper presents a high performance design for ContextBased Adaptive Variable Length Coding (CAVLC) used in the H.264/ AVC standard. A two-stage encoder is proposed to make the scan and encode stage work simultaneously. The scan engine scans four coefficients at each cycle. Parallel encoder for four “levels” and parallel encoder for four “Run before” are adopted to accelerate the encode engi...

In current Deep Submicron (DSM) era, interconnects play important role in overall performance of the chip. The factors such as power dissipation and crosstalk through RC modeled interconnects substantially affect the entire working of the chip. Therefore, to enhance the performance, minimization or elimination of coupling between interconnects is essential. Bus-invert method is the best method ...

In order to achieve adaptive channel coding and adaptive modulation, the main causes of degradation to system performance are the decoder selection error and modulator estimation error. The utilization of supplementary information, in an estimation system utilizing channel estimation results, blind modulation estimation, and blind encoder estimation using several decoders information and encode...

The information about 3D atomic coordinates of chemical structures is valuable knowledge in many respect. For large sets of different structures, the computation or measurement of these coordinates is an expensive process. Therefore, the originator of such a data set is interested in enforcing his intellectual property right. In this paper, a method for copyright protection of chemical structur...

We describe a simple method for high-precision rotary angle encoder calibration for longrange angular errors. By using a redesigned electronic nulling autocollimator, an opticalpolygon artifact is calibrated simultaneously with determining the encoder error function over a rotation of 2π rad. The technique is applied to the NIST vacuum double crystal spectrometer, which depends on precise measu...