While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on the primary task. Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer. This penalty encourages activations to be smooth either on a predetermined graph or on a feature-space graph learned from the data via co-activations of a hidden layer of the neural network. We show numerous uses for this additional structure including cluster indication and visualization in biological and image data sets.

RNA-seq is exponentially becoming the de facto standard approach to compel considerable advantages over conventional technologies such as micro array by directly sequencing transcripts in gene expression profile. As the cost to sequencing is dropping rapidly, studies to dynamic change of gene expression in a given biological system over time have shown steady growth over the past few years as micro array, however, statistical approaches to characterize dynamic temporal complexities are currently elusive. In differential gene expression analysis, as somehow limited but intuitive solutions, static differential expression methods without respect to time can be applied, which do not take into account the inherent dependencies in time series explicitly that the expression patterns at later stages are dependent on patterns at earlier stages. We present a statistical framework to define dynamic gene expression patterns over time using trajectory index and Hidden Markov Model (HMM) approach in time series RNA-seq data, and our methods are validated through Markov Chain Monte Carlo (MCMC) simulation study in time series dependent data. The utility of the dynamic specific methods for temporal RNA-seq is demonstrated by application to the analyses of gene expression patterns in RNA-seq seven real data sets and MCMC simulation study in details.

Abstract — This paper presents how SCTP can stall in multihomed scenarios during failover and under certain circumstances. A stall is where an SCTP end-point ceases to communicate for an extended period of time, but does not report any error to the upper layer. This paper presents two different sets of circumstances where a stall can occur: firstly when there is an underestimation of the Retransmission Time-Out (RTO) value for a redundant network path; and secondly when a network error occurs that causes only SACKs to be lost, which confuses the SCTP sender about which network path is operational. Solutions to both of these stalls are presented that include modifying the RTO value, applying Karn’s algorithm to path monitoring and ensuring the destination address selection policy for SACKs is changed. This paper also presents a mechanism to de-couple data acknowledgement and path monitoring when using multi-homed transport protocols, which should remove the ambiguity about path monitoring and offers a universal solution to the stall. I.