Estimation of uncertainty in deep learning models is of vital importance, especially in medical imaging, where reliance on inference without taking into account uncertainty could lead to misdiagnosis. Recently, the probabilistic Variational AutoEncoder (VAE) has become a popular model for anomaly detection in applications such as lesion detection in medical images. The VAE is a generative graphical model that is used to learn the data distribution from samples and then generate new samples from this distribution. By training on normal samples, the VAE can be used to detect inputs that deviate from this learned distribution. The VAE models the output as a conditionally independent Gaussian characterized by means and variances for each output dimension. VAEs can therefore use reconstruction probability instead of reconstruction error for anomaly detection. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. We describe an alternative approach that avoids this variance shrinkage problem by using quantile regression. Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection. Results on simulated and Fashion MNIST data demonstrate the effectiveness of our approach. We also show how our approach can be used for principled heterogeneous thresholding for lesion detection in brain images.

We consider surveillance-evasion differential games, where a pursuer must try to constantly maintain visibility of a moving evader. The pursuer loses as soon as the evader becomes occluded. Optimal controls for game can be formulated as a Hamilton-Jacobi-Isaac equation. We use an upwind scheme to compute the feedback value function, corresponding to the end-game time of the differential game. Although the value function enables optimal controls, it is prohibitively expensive to compute, even for a single pursuer and single evader on a small grid. We consider a discrete variant of the surveillance-game. We propose two locally optimal strategies based on the static value function for the surveillance-evasion game with multiple pursuers and evaders. We show that Monte Carlo tree search and self-play reinforcement learning can train a deep neural network to generate reasonable strategies for on-line game play. Given enough computational resources and offline training time, the proposed model can continue to improve its policies and efficiently scale to higher resolutions.

To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces. (2) without the unified information among clients in FURL, the representations across clients would be misaligned. To address these challenges, we propose Federated Constrastive Averaging with dictionary and alignment (FedCA) algorithm. FedCA is composed of two key modules: (1) dictionary module to aggregate the representations of samples from each client and share with all clients for consistency of representation space and (2) alignment module to align the representation of each client on a base model trained on a public data. We adopt the contrastive loss for local model training. Through extensive experiments with three evaluation protocols in IID and Non-IID settings, we demonstrate that FedCA outperforms all baselines with significant margins.

Feature importance ranking has become a powerful tool for explainable AI. However, its nature of combinatorial optimization poses a great challenge for deep learning. In this paper, we propose a novel dual-net architecture consisting of operator and selector for discovery of an optimal feature subset of a fixed size and ranking the importance of those features in the optimal subset simultaneously. During learning, the operator is trained for a supervised learning task via optimal feature subset candidates generated by the selector that learns predicting the learning performance of the operator working on different optimal subset candidates. We develop an alternate learning algorithm that trains two nets jointly and incorporates a stochastic local search procedure into learning to address the combinatorial optimization challenge. In deployment, the selector generates an optimal feature subset and ranks feature importance, while the operator makes predictions based on the optimal subset for test data. A thorough evaluation on synthetic, benchmark and real data sets suggests that our approach outperforms several state-of-the-art feature importance ranking and supervised feature selection methods.

Data is the fuel for machine learning, but the data needs to be accurately labeled for the machines to learn. To that end, data training startup Dataloop yesterday unveiled that it's received $11 million in Series A funding to build SaaS data pipelines that combine human supervision of the data annotation process, along with data management capabilities. Today's computer vision models are extremely powerful, and the ones based on deep learning approaches can exceed human capabilities. From self-driving cars navigating in the world to programs that can accurate diagnose diseases in MRI images, the potential uses for Ais built upon convolutional neural networks are astonishingly wide. However, there's a catch (there always is).

To comply with regulation is one of the last reasons someone should think about making artificial intelligence more explainable. Sure, there are benefits -- decisions made by a replicable, well-understood process are more trustworthy than those made by a black-box. Most importantly, it makes your business managers happy by providing a higher return on investments. The good news is that there are hacks your team can start working on right now to make things easier. One of the challenges in training an artificially intelligent model is that there is no way to make incremental improvements.

The emergence of Industrial Internet of Things (IIoT) leads in developing automated environments, such as smart factories, smart airports and smart healthcare systems. AI applications enable the automation and data analytics across industrial technologies, including the Internet of Things (IoT), cloud and edge, and fog computing paradigms. Existing Artificial Intelligence (AI), especially Deep Learning (DL) models, still suffer from designing a generalized architecture that reveals semantics and contexts of models, considering Human-in-the-loop (HITL). Adversarial Machine Learning (AML) models have been widely utilized to fool DL applications using malicious actors. This makes a great interest to establish white-box models, rather than black-box ones, to determine their trustworthiness and reliability in business problems in IIoT networks.

Data is the fuel for machine learning, but the data needs to be accurately labeled for the machines to learn. To that end, data training startup Dataloop yesterday unveiled that it's received $11 million in Series A funding to build SaaS data pipelines that combine human supervision of the data annotation process, along with data management capabilities. Today's computer vision models are extremely powerful, and the ones based on deep learning approaches can exceed human capabilities. From self-driving cars navigating in the world to programs that can accurate diagnose diseases in MRI images, the potential uses for Ais built upon convolutional neural networks are astonishingly wide. However, there's a catch (there always is).

C is ideal for dynamic load balancing, adaptive caching, and developing large big data frameworks, and libraries. Google's MapReduce, MongoDB, most of the deep learning libraries listed below have been implemented using C . Scylla known for its ultra-low latency and extremely high throughput is coded using C acts as a replacement to Apache Cassandra and Amazon DynamoDB. With some of the unique advantages of C as a programming language, (including memory management, performance characteristics, and systems programming), it definitely serves as one of the most efficient tools for developing fast scalable Data Science and Big Data libraries. Further, Julia (a compiled and interactive language – developed from MIT) is emerging as a potential competitor to Python in the field of scientific computing and data processing. Its fast processing speed, parallelism, static along with dynamic typing and C bindings for plugging in libraries, has eased the job for developers/data scientists to integrate and use C as data science and big data library.

Modern AI has produced models that exceed human performance across countless tasks. Now, an international research team is suggesting AI might become even more efficient and reliable if it learns to think more like worms. In a paper recently published in Nature Machine Intelligence journal, the team from MIT CSAIL, TU Wien in Vienna, and IST Austria proposes an AI system that mimics biological models. The system was developed based on the brains of tiny animals such as threadworms and is able to control a vehicle using just a small number of artificial neurons. The researchers say the system has decisive advantages over other deep learning models because it copes much better with noisy input, and, because of its simplicity, its operations can be explained in detail -- alleviating the "black box" concerns affecting today's deep AI models. Explains TU Wien Cyber-Physical Systems head Professor Radu Grosu in a project press release: "For years, we have been investigating what we can learn from nature to improve deep learning.