Saltwater aquaria are living systems that support a complex biological community of fish, invertebrates, and microbes. The health and maintenance of saltwater tanks are pressing concerns for home hobbyists, zoos, and professionals in the aquarium trade; however, we do not yet understand the underlying microbial species interactions and community dynamics which contribute to tank setup and conditioning. This report provides a detailed view of ecological succession and changes in microbial community assemblages in two saltwater aquaria which were sampled over a 3-month period, from initial tank setup and conditioning with “live rocks” through subsequent tank cleanings and water replacement. Our results showed that microbial succession appeared to be consistent and replicable across both aquaria. However, changes in microbial communities did not always correlate with water chemistry measurements, and aquarium microbial communities appear to have shifted among multiple stable states without any obvious buildup of undesirable nitrogen compounds in the tank environment.

Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement. This research focuses on facial attribute prediction using a novel deep learning formulation, termed as R-Codean autoencoder. The paper first presents Cosine similarity based loss function in an autoencoder which is then incorporated into the Euclidean distance based autoencoder to formulate R-Codean. The proposed loss function thus aims to incorporate both magnitude and direction of image vectors during feature learning. Further, inspired by the utility of shortcut connections in deep models to facilitate learning of optimal parameters, without incurring the problem of vanishing gradient, the proposed formulation is extended to incorporate shortcut connections in the architecture. The proposed R-Codean autoencoder is utilized in facial attribute prediction framework which incorporates patch-based weighting mechanism for assigning higher weights to relevant patches for each attribute. The experimental results on publicly available CelebA and LFWA datasets demonstrate the efficacy of the proposed approach in addressing this challenging problem.

With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Even if the source code is available, then re-implementing research papers in a different library is a daunting task. To address these challenges, we propose a novel extensible approach, DLPaper2Code, to extract and understand deep learning design flow diagrams and tables available in a research paper and convert them to an abstract computational graph. The extracted computational graph is then converted into execution ready source code in both Keras and Caffe, in real-time. An arXiv-like website is created where the automatically generated designs is made publicly available for 5,000 research papers. The generated designs could be rated and edited using an intuitive drag-and-drop UI framework in a crowd sourced manner. To evaluate our approach, we create a simulated dataset with over 216,000 valid deep learning design flow diagrams using a manually defined grammar. Experiments on the simulated dataset show that the proposed framework provide more than 93% accuracy in flow diagram content extraction.