The increased need for automatic medical image segmentation has been created due to the enormous usage of modern medical imaging in technology. Despite this large need, the current medical image segmentation platforms do not provide required functionalities for the plain setup of medical image segmentation pipelines. Therefore this paper introduces the open-source Python library MIScnn. MIScnn is an opensource framework with intuitive APIs allowing the fast setup of medical image segmentation pipelines with Convolutional Neural Network and DeepLearning models in just a few lines of code. The objective of MIScnn according to paper is to provide a framework API that can be allowing the fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g.

IBM today announced it will apply a range of artificial intelligence (AI) technologies to automate the management of IT operations and modernize applications, also known as AIOps. Announced at IBM's Think Digital conference, Watson AIOps leverages algorithms to continuously optimize IT operations while Accelerator for Application Modernization with AI is a suite of tools that leverage continuous learning and interpretable AI models to help organizations stay current as modern of technology and platforms evolve. Made available as part of a Cloud Modernization Service engagement, the Application Modernization with AI tools span a range of tasks from applying AI to more accurately identifying software components that should be deployed as containers or converted into microservices to applying symbolic reasoning to dynamically define modernization steps that are surfaced via a natural language processing (NLP) engine. Watson AIOps, meanwhile, applies machine and deep learning algorithms to time series data, semi-structured logs, structured data and unstructured data spanning both IT incidents and human conversations to track the timeline of an issue. It then uses that data to correlate root causes, create an explainable diagnosis and generate a recommendation for the best course of action. Built on top of an instance of the OpenShift platform that IBM gained via its acquisition of Red Hat, the Watson AIOps also leverages semantic search techniques that can relate the current incident to past incidents to provide additional context.

At present, recognition of the Bangla handwriting compound character has been an essential issue for many years. In recent years there have been application-based researches in machine learning, and deep learning, which is gained interest, and most notably is handwriting recognition because it has a tremendous application such as Bangla OCR. MatrriVasha, the project which can recognize Bangla, handwritten several compound characters. Currently, compound character recognition is an important topic due to its variant application, and helps to create old forms, and information digitization with reliability. But unfortunately, there is a lack of a comprehensive dataset that can categorize all types of Bangla compound characters. MatrriVasha is an attempt to align compound character, and it's challenging because each person has a unique style of writing shapes. After all, MatrriVasha has proposed a dataset that intends to recognize Bangla 120(one hundred twenty) compound characters that consist of 2552(two thousand five hundred fifty-two) isolated handwritten characters written unique writers which were collected from within Bangladesh. This dataset faced problems in terms of the district, age, and gender-based written related research because the samples were collected that includes a verity of the district, age group, and the equal number of males, and females. As of now, our proposed dataset is so far the most extensive dataset for Bangla compound characters. It is intended to frame the acknowledgment technique for handwritten Bangla compound character. In the future, this dataset will be made publicly available to help to widen the research.

Current explanation techniques towards a transparent Convolutional Neural Network (CNN) mainly focuses on building connections between the human-understandable input features with models' prediction, overlooking an alternative representation of the input, the frequency components decomposition. In this work, we present an analysis of the connection between the distribution of frequency components in the input dataset and the reasoning process the model learns from the data. We further provide quantification analysis about the contribution of different frequency components toward the model's prediction. We show that the vulnerability of the model against tiny distortions is a result of the model is relying on the high-frequency features, the target features of the adversarial (black and white-box) attackers, to make the prediction. We further show that if the model develops stronger association between the low-frequency component with true labels, the model is more robust, which is the explanation of why adversarially trained models are more robust against tiny distortions.

Reducing domain divergence is a key step in transfer learning problems. Existing works focus on the minimization of global domain divergence. However, two domains may consist of several shared subdomains, and differ from each other in each subdomain. In this paper, we take the local divergence of subdomains into account in transfer. Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains. A Manifold Maximum Mean Discrepancy (M3D) is developed to measure the local distribution discrepancy in each manifold. We then propose a general framework, called Transfer with Manifolds Discrepancy Alignment (TMDA), to couple the discovery of data manifolds with the minimization of M3D. We instantiate TMDA in the subspace learning case considering both the linear and nonlinear mappings. We also instantiate TMDA in the deep learning framework. Extensive experimental studies demonstrate that TMDA is a promising method for various transfer learning tasks.

Model Stealing (MS) attacks allow an adversary with black-box access to a Machine Learning model to replicate its functionality, compromising the confidentiality of the model. Such attacks train a clone model by using the predictions of the target model for different inputs. The effectiveness of such attacks relies heavily on the availability of data necessary to query the target model. Existing attacks either assume partial access to the dataset of the target model or availability of an alternate dataset with semantic similarities. This paper proposes MAZE -- a data-free model stealing attack using zeroth-order gradient estimation. In contrast to prior works, MAZE does not require any data and instead creates synthetic data using a generative model. Inspired by recent works in data-free Knowledge Distillation (KD), we train the generative model using a disagreement objective to produce inputs that maximize disagreement between the clone and the target model. However, unlike the white-box setting of KD, where the gradient information is available, training a generator for model stealing requires performing black-box optimization, as it involves accessing the target model under attack. MAZE relies on zeroth-order gradient estimation to perform this optimization and enables a highly accurate MS attack. Our evaluation with four datasets shows that MAZE provides a normalized clone accuracy in the range of 0.91x to 0.99x, and outperforms even the recent attacks that rely on partial data (JBDA, clone accuracy 0.13x to 0.69x) and surrogate data (KnockoffNets, clone accuracy 0.52x to 0.97x). We also study an extension of MAZE in the partial-data setting and develop MAZE-PD, which generates synthetic data closer to the target distribution. MAZE-PD further improves the clone accuracy (0.97x to 1.0x) and reduces the query required for the attack by 2x-24x.

Uncertainties in a structure is inevitable, which generally lead to variation in dynamic response predictions. For a complex structure, brute force Monte Carlo simulation for response variation analysis is infeasible since one single run may already be computationally costly. Data driven meta-modeling approaches have thus been explored to facilitate efficient emulation and statistical inference. The performance of a meta-model hinges upon both the quality and quantity of training dataset. In actual practice, however, high-fidelity data acquired from high-dimensional finite element simulation or experiment are generally scarce, which poses significant challenge to meta-model establishment. In this research, we take advantage of the multi-level response prediction opportunity in structural dynamic analysis, i.e., acquiring rapidly a large amount of low-fidelity data from reduced-order modeling, and acquiring accurately a small amount of high-fidelity data from full-scale finite element analysis. Specifically, we formulate a composite neural network fusion approach that can fully utilize the multi-level, heterogeneous datasets obtained. It implicitly identifies the correlation of the low- and high-fidelity datasets, which yields improved accuracy when compared with the state-of-the-art. Comprehensive investigations using frequency response variation characterization as case example are carried out to demonstrate the performance.

We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces. The proposed approach is motivated by the recent successes of neural networks and deep learning, in combination with ideas from model reduction. This combination results in a neural network approximation which, in principle, is defined on infinite-dimensional spaces and, in practice, is robust to the dimension of finite-dimensional approximations of these spaces required for computation. For a class of input-output maps, and suitably chosen probability measures on the inputs, we prove convergence of the proposed approximation methodology. Numerically we demonstrate the effectiveness of the method on a class of parametric elliptic PDE problems, showing convergence and robustness of the approximation scheme with respect to the size of the discretization, and compare our method with existing algorithms from the literature.

We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from $\epsilon$-$\delta$ differential privacy and the inception score. Our experiments uncover a saturated training regime where an increasing privacy budget adds little to the quality of generated images. We also explain analytically why differentially private Adam optimization is independent of the gradient clipping parameter. Furthermore, we highlight common errors in previous works on differentially private deep learning, which we uncovered in recent literature. Throughout the treatment of the subject, we hope to prevent erroneous estimates of anonymity in the future.

Neural Ordinary Differential Equations (ODEs) are elegant reinterpretations of deep networks where continuous time can replace the discrete notion of depth, ODE solvers perform forward propagation, and the adjoint method enables efficient, constant memory backpropagation. Neural ODEs are universal approximators only when they are non-autonomous, that is, the dynamics depends explicitly on time. We propose a novel family of Neural ODEs with time-varying weights, where time-dependence is non-parametric, and the smoothness of weight trajectories can be explicitly controlled to allow a tradeoff between expressiveness and efficiency. Using this enhanced expressiveness, we outperform previous Neural ODE variants in both speed and representational capacity, ultimately outperforming standard ResNet and CNN models on select image classification and video prediction tasks.