Domain-specific SoCs (DSSoCs) are an attractive solution for domains with extremely stringent power, performance, and area constraints. However, DSSoCs suffer from two fundamental complexities. On the one hand, their many specialized hardware blocks result in complex systems and thus high development effort. On the other hand, their many system knobs expand the complexity of design space, making the search for the optimal design difficult. Thus to reach prevalence, taming such complexities is necessary. To address these challenges, in this work, we identify the necessary features of an early-stage design space exploration framework that targets the complex design space of DSSoCs and provide an instance of one such framework that we refer to as FARSI. FARSI provides an agile system-level simulator with speed up and accuracy of 8,400× and 98.5% compared to Synopsys Platform Architect. FARSI also provides an efficient exploration heuristic and achieves up to 62× and 35× improvement in convergence time compared to the classic simulated annealing (SA) and modern Multi-Objective Optimistic Search. This is done by augmenting SA with architectural reasoning such as locality exploitation and bottleneck relaxation. Furthermore, we embed various co-design capabilities and show that, on average, they have a 32% impact on the convergence rate. Finally, we demonstrate that using development-cost-aware policies can lower the system complexity, both in terms of the component count and variation by as much as 60% and 82% (e.g., for Network-on-a-Chip subsystem), respectively.

Good generalization capability is an important quality of well-trained and robust neural networks. However, networks usually struggle when faced with samples outside the training distribution. Mixup is a technique that improves generalization, reduces memorization, and increases adversarial robustness. We apply a variant of Mixup called Manifold Mixup to the sentence classification problem, and present the results along with an ablation study. Our methodology outperforms CNN, LSTM, and vanilla BERT models in generalization.

Models with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution.We introduce Emix, a data augmentation method that uses interpolations of word embeddings and hidden layer representations to construct virtual examples.We show that Emix shows significant improvements over previously used interpolation based regularizers and data augmentation techniques.We also demonstrate how our proposed method is more robust to sparsification.We highlight the merits of our proposed methodology by performing thorough quantitative and qualitative assessments.

Recently, several image processing and deep learning techniques have been applied to automate the detection of Acute Lymphoblastic Leukemia cells (ALL). However, most of them have consistently focused on classification mature stage cell images into binary categories of ALL or normal cells. The real impetus of biomedical imaging lies in detecting early-stage cases since early-stage ALL cells have unintuitive global contextual and local spatial features, making their detection non-trivial. To this effect, we propose a novel architecture termed as Mixup Multi-Attention Multi-Task Learning Model (MMA-MTL), which introduces Pointwise Attention Convolution Layers and Local Spatial Attention blocks to capture global and local features simultaneously. We also introduce Rademacher Paired Sampling Mixup to prevent memorization of training data in cases of limited categorical shift. Our proposed method shows competitive performance on the ISBI-2019 CNMC dataset and benchmarks appropriate design choices for future biomedical imaging tasks.