Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions associated with the faulty behavior? Recent works on decomposing a fully connected neural network (FCNN) and convolutional neural network (CNN) into modules have shown the value of engineering deep models in this manner, which is standard in traditional SE but foreign for deep learning models. However, prior works focus on the image-based multi-class classification problems and cannot be applied to RNN due to (a) different layer structures, (b) loop structures, (c) different types of input-output architectures, and (d) usage of both non-linear and logistic activation functions. In this work, we propose the first approach to decompose an RNN into modules. We study different types of RNNs, i.e., Vanilla, LSTM, and GRU. Further, we show how such RNN modules can be reused and replaced in various scenarios. We evaluate our approach against 5 canonical datasets (i.e., Math QA, Brown Corpus, Wiki-toxicity, Cline OOS, and Tatoeba) and 4 model variants for each dataset. We found that decomposing a trained model has a small cost (Accuracy: -0.6%, BLEU score: +0.10%). Also, the decomposed modules can be reused and replaced without needing to retrain.

Summary The objective of this article is to increase the efficiency of face recognition in the aspect of a dynamic frame. Studies were carried out that focus on maintaining the high detection rate as well as increasing the accuracy. The study was conducted by considering the current recording of the dynamic frame of randomly selected people walking on a treadmill. Here, the variety of facial features was studied and extracted using different viewing angles on the subject. The existence of a huge amount of datasets and economical processing power is subject to value enhancement in the presence of a convolutional neural network (CNN) on different object identification and realization criteria. These methodologies with excellent knowledge of deep learning techniques that subjects to enhance the potential of the machine to learn the face values. CNN is capable to identify faces, positive positioning facial benchmarks, estimating postures and understanding faces in interconnected images and dynamic video frames. In this article, we present a novel phase detector technique that is rapid and has the potential of recognizing faces with huge changes. This is performed by a technique of using adopted CNN and recurrent neural network's subpart long‐short term memory technique in a particular way so that the objective of bringing improvement in the reorganization procedure can be fulfilled. And this was completed by getting 97.5%–98.1% of accuracy is sustained in this.

Movements of articulators (e.g., tongue, lips and jaw) in different speaking rates are related in a complex manner. In this work, we examine the underlying function to transform articulatory movements involved in producing speech at a neutral speaking rate into those at fast and slow speaking rates (N2F and N2S). For this we use articulatory movement data collected from five subjects using an Electromagnetic articulograph at neutral, fast and slow speaking rates. As candidate transformation functions (TF), we use affine transformations with a diagonal matrix and a full matrix and a nonlinear function modeled by a deep neural network (DNN). Since the duration of an utterance in different speaking rates would typically be unequal, it is required to time align the articulatory movement trajectories, which, in turn, affects the TF learnt. Therefore, we propose an iterative algorithm to alternately optimize for the TF and the time alignments. Subject specific experiments reveal that while N2F transformation can be well described by an affine transformation with a full matrix, N2S transformation is better represented by a more complex nonlinear function modeled by a DNN. This could be because subjects exhibit gross articulatory movements during fast speech and hyper-articulate while producing slow speech.