e success of deep learning depends on nding an architecture to t the task. As deep learning has scaled up to more challenging tasks, the architectures have become di cult to design by hand.is paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution. By extending existing neuroevolution methods to topology, components, and hyperparameters, this method achieves results comparable to best human designs in standard benchmarks in object recognition and language modeling. It also supports building a real-world application of automated image captioning on a magazine website. Given the anticipated increases in available computing power, evolution of deep networks is promising approach to constructing deep learning applications in the future.

Cross-Language Information Retrieval (CLIR) is a sub field of Information Retrieval (IR). Like IR, in CLIR for a particular information need, we have to find relevant information or documents containing such information. In CLIR multiple tools must be developed to match terms containing same meaning in different languages. The usual solution is to translate the query and/or the documents before performing the search. So translation is pivotal activity in CLIR. In CLIR a wide range of techniques were proposed in the literature for translation. This paper presents a detailed insight of these techniques, with a special emphasis on recent developments.

No abstract

<span id="docs-internal-guid-5b69f940-7fff-f443-1f09-a00e5e983714"><span>In cross-language information retrieval (CLIR), the neural machine translation (NMT) plays a vital role. CLIR retrieves the information written in a language which is different from the user's query language. In CLIR, the main concern is to translate the user query from the source language to the target language. NMT is useful for translating the data from one language to another. NMT has better accuracy for different languages like English to German and so-on. In this paper, NMT has applied for translating English to Indian languages, especially for Telugu. Besides NMT, an effort is also made to improve accuracy by applying effective preprocessing mechanism. The role of effective preprocessing in improving accuracy will be less but countable. Machine translation (MT) is a data-driven approach where parallel corpus will act as input in MT. NMT requires a massive amount of parallel corpus for performing the translation. Building an English - Telugu parallel corpus is costly because they are resource-poor languages. Different mechanisms are available for preparing the parallel corpus. The major issue in preparing parallel corpus is data replication that is handled during preprocessing. The other issue in machine translation is the out-of-vocabulary (OOV) problem. Earlier dictionaries are used to handle OOV problems. To overcome this problem the rare words are segmented into sequences of subwords during preprocessing. The parameters like accuracy, perplexity, cross-entropy and BLEU scores shows better translation quality for NMT with effective preprocessing.</span></span>

Gastro retentive dosage forms have potential for use as controlled- release drug delivery systems. Gastro retentive floating drug delivery systems have a bulk density lower than that of gastric fluids and thus increase residence time of drug in stomach and provide controlled delivery of many drugs. The aim of the present study is formulation and characterization of floating microspheres using Sitagliptin as a model drug for the management of type-2 diabetes mellitus. Floating microspheres were prepared by oil-in-water emulsion solvent evaporation technique using ethyl cellulose and eudragit S-100 as release retarding polymers. The floating microspheres were evaluated for percentage yield (%), particle size, drug content, drug entrapment efficiency, in-vitro floating ability and in-vitro drug release studies. The surface morphology of prepared microspheres was characterized by scanning electron microscopy. The microspheres were found to be spherical in shape and porous in nature. Compatibility studies were performed by fourier transform infrared (FTIR) technique. The prepared microspheres showed prolonged drug release of 12 h and remain buoyant for more than 12 h. In-vitro release kinetics were studied in different release kinetics models like zero order, first order, higuchi and korsmeyer peppas model and the best fit model was found to be higuchi plot with release exponent n value less than 0.89. It was concluded that developed floating microspheres of Sitagliptin offers a suitable and practical approach for prolonged release of drug over an extended period of time and thus oral bioavailability, efficacy and patient compliance is improved.