Learning a disentangled representation of the latent space has become one of the most fundamental problems studied in computer vision. Recently, many Generative Adversarial Networks (GANs) have shown promising results in generating high fidelity images. However, studies to understand the semantic layout of the latent space of pre-trained models are still limited. Several works train conditional GANs to generate faces with required semantic attributes. Unfortunately, in these attempts, the generated output is often not as photo-realistic as the unconditional state-of-the-art models. Besides, they also require large computational resources and specific datasets to generate high fidelity images. In our work, we have formulated a Markov Decision Process (MDP) over the latent space of a pre-trained GAN model to learn a conditional policy for semantic manipulation along specific attributes under defined identity bounds. Further, we have defined a semantic age manipulation scheme using a locally linear approximation over the latent space. Results show that our learned policy samples high fidelity images with required age alterations, while preserving the identity of the person.

MOTIVATION: Accurate prediction of binding between a major histocompatibility complex (MHC) allele and a peptide plays a major role in the synthesis of personalized cancer vaccines. The immune system struggles to distinguish between a cancerous and a healthy cell. In a patient suffering from cancer who has a particular MHC allele, only those peptides that bind with the MHC allele with high affinity, help the immune system recognize the cancerous cells. RESULTS: MHCAttnNet is a deep neural model that uses an attention mechanism to capture the relevant subsequences of the amino acid sequences of peptides and MHC alleles. It then uses this to accurately predict the MHC-peptide binding. MHCAttnNet achieves an AUC-PRC score of 94.18% with 161 class I MHC alleles, which outperforms the state-of-the-art models for this task. MHCAttnNet also achieves a better F1-score in comparison to the state-of-the-art models while covering a larger number of class II MHC alleles. The attention mechanism used by MHCAttnNet provides a heatmap over the amino acids thus indicating the important subsequences present in the amino acid sequence. This approach also allows us to focus on a much smaller number of relevant trigrams corresponding to the amino acid sequence of an MHC allele, from 9251 possible trigrams to about 258. This significantly reduces the number of amino acid subsequences that need to be clinically tested. AVAILABILITY AND IMPLEMENTATION: The data and source code are available at https://github.com/gopuvenkat/MHCAttnNet.

Ability to predict the future performance of a storage system is critical for its efficient management. A modern storage system is a very complex combination of hardware and software elements and inferring its state from those of its individual components is practically impossible. Moreover, the state of the system undergoes continuous changes due to diverse and evolving workloads, frequent configuration changes and natural degradation in components. This paper presents an approach to predict the future response time of a storage system by applying a combination of machine learning techniques on the data of its internal parameters. To the best of our knowledge, this is the first attempt to quantify the response time of a storage system directly from the time-series of its internal parameters. We present a systematic experimental setup for collecting the system data and for measuring its response time while loading the system with different standard workloads. Another novel contribution of the paper is a combination of time-series forecasting model followed by a regression model to predict the response time repeatedly in real-time. The said model is shown to be able to repeatedly predict fairly accurate 15-minutes-ahead response time values using the system data of the past 20-minutes' window. It is shown that the validation calculations typically complete within ~30 seconds on an average using a computer of moderate configurations making the presented model applicable for practically reasonable prediction horizons. The design of the model is such that it can be adaptively tuned online at regular intervals as more system data is observed.

Tertiary storage areas are integral parts of compute environment and are primarily used to store vast amount of data that is generated from any scientific/industry workload. Modelling the possible pattern of usage of storage area helps the administrators to take preventive actions and guide users on how to use the storage areas which are tending towards slower to unresponsive state. Treating the storage performance parameters as a time series data helps to predict the possible values for the next ‘n’ intervals using forecasting models like ARIMA. These predicted performance parameters are used to classify if the entire storage area or a logical component is tending towards unresponsiveness. Classification is performed using the proposed Skyline ranked Ensemble model with two possible classes, i.e. high response state and low response state. Heavy load scenarios were simulated and close to 95% of the behaviour were explained using the proposed model.