Aerendir Mobile Inc. will merge its mathematical deep learning cores and AI infrastructure with innovative SiFive, Inc., RISC-V Core IP to enable a new low-cost board format for deep learning. This combined, unique approach will radically decrease the cost of true AI, allowing it to be enabled at the IoT Edge and End Point inside affordable devices. Aerendir and SiFive expect that the IoT market, bolstered by future 5G networks, will require the most cost-effective high-end distributed learning capabilities. As data collection continues to grow and outstrip the ability of datacenters to store, process and analyze new devices at the edge, end point can help to make accurate machine learning decisions. Local data analysis reduces network congestion and latency, improving local device performance and helping to send important data to the cloud for further analysis.

Technological change is the only constant in today's business world, disrupting everything from large organizations to small start-ups. Disruption affects everyone, but will you be the disruptor or the disrupted? You must pay close attention to the Hard Trends shaping the future of your industry, your business, and the outside world to identify opportunities used to innovate and grow rapidly, additionally using those Hard Trends to solve any problems your organization and customers might have before they occur. The shared definition and understanding of the words we use is an issue in business. While several companies are on course to use artificial intelligence (AI), machine learning (ML), and deep learning (DL), others hardly understand the fundamental differences between these powerful technologies.

Trying to read this article is a complicated task from the neuroscientific standpoint. At this time you are probably bombarded with emails, news, notifications on our phone, the usual annoying coworker interrupting and other distractions that cause your brain to spin on many directions. In order to read this tiny article or perform many other cognitive tasks, you need to focus, you need attention. Attention is a cognitive skill that is pivotal to the formation of knowledge. However, the dynamics of attention have remained a mystery to neuroscientists for centuries and, just recently, that we have had major breakthroughs that help to explain how attention works.

As a mental disorder progresses, it may affect brain structu re, but brain function expressed in brain dynamics is affected much earlier. Captu ring the moment when brain dynamics express the disorder is crucial for early dia gnosis. The traditional approach to this problem via training classifiers either pro ceeds from handcrafted features or requires large datasets to combat the m n problem when a high dimensional fMRI volume only has a single label that carries le arning signal. Large datasets may not be available for a study of each disorder, or rare disorder types or subpopulations may not warrant for them. In this paper, w e demonstrate a self-supervised pre-training method that enables us to pre -train directly on fMRI dynamics of healthy control subjects and transfer the learn ing to much smaller datasets of schizophrenia. Not only we enable classificatio n of disorder directly based on fMRI dynamics in small data but also significantly sp eed up the learning when possible. This is encouraging evidence of informat ive transfer learning across datasets and diagnostic categories.

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a low-dimensional embedding using a pretrained model, and then performs efficient search within the embedding space to attack an unknown target network. The method produces adversarial perturbations with high level semantic patterns that are easily transferable. We show that this approach can greatly improve the query efficiency of black-box adversarial attack across different target network architectures. We evaluate our approach on MNIST, ImageNet and Google Cloud Vision API, resulting in a significant reduction on the number of queries. We also attack adversarially defended networks on CIFAR10 and ImageNet, where our method not only reduces the number of queries, but also improves the attack success rate.

Machine learning (ML), deep learning (DL), and artificial intelligence (AI) are of increasing importance in biomedicine. The goal of this work is to show progress in ML in digital health, to exemplify future needs and trends, and to identify any essential prerequisites of AI and ML for precision health. High-throughput technologies are delivering growing volumes of biomedical data, such as large-scale genome-wide sequencing assays, libraries of medical images, or drug perturbation screens of healthy, developing, and diseased tissue. Multi-omics data in biomedicine is deep and complex, offering an opportunity for data-driven insights and automated disease classification. Learning from these data will open our understanding and definition of healthy baselines and disease signatures. State-of-the-art applications of deep neural networks include digital image recognition, single cell clustering, and virtual drug screens, demonstrating breadths and power of ML in biomedicine. Significantly, AI and systems biology have embraced big data challenges and may enable novel biotechnology-derived therapies to facilitate the implementation of precision medicine approaches.

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction by~\citet{fredrikson2014privacy}, such attacks have raised serious concerns given that training data usually contain privacy sensitive information. Thus far, successful model-inversion attacks have only been demonstrated on simple models, such as linear regression and logistic regression. Previous attempts to invert neural networks, even the ones with simple architectures, have failed to produce convincing results. Here we present a novel attack method, termed the \emph{generative model-inversion attack}, which can invert deep neural networks with high success rates. Rather than reconstructing private training data from scratch, we leverage partial public information, which can be very generic, to learn a distributional prior via generative adversarial networks (GANs) and use it to guide the inversion process. Moreover, we theoretically prove that a model's predictive power and its vulnerability to inversion attacks are indeed two sides of the same coin---highly predictive models are able to establish a strong correlation between features and labels, which coincides exactly with what an adversary exploits to mount the attacks. Our extensive experiments demonstrate that the proposed attack improves identification accuracy over the existing work by about $75\%$ for reconstructing face images from a state-of-the-art face recognition classifier. We also show that differential privacy, in its canonical form, is of little avail to defend against our attacks.

Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As real-world graphs are often incomplete and noisy, treating them as ground-truth information, which is a common practice in most GCNs, unavoidably leads to sub-optimal solutions. Existing efforts for addressing this problem either involve an over-parameterized model which is difficult to scale, or simply re-weight observed edges without dealing with the missing-edge issue. This paper proposes a novel framework called Graph-Revised Convolutional Network (GRCN), which avoids both extremes. Specifically, a GCN-based graph revision module is introduced for predicting missing edges and revising edge weights w.r.t. downstream tasks via joint optimization. A theoretical analysis reveals the connection between GRCN and previous work on multigraph belief propagation. Experiments on six benchmark datasets show that GRCN consistently outperforms strong baseline methods by a large margin, especially when the original graphs are severely incomplete or the labeled instances for model training are highly sparse.

Robust anomaly detection is a requirement for monitoring complex modern systems with applications such as cyber-security, fraud prevention, and maintenance. These systems generate multiple correlated time series that are highly seasonal and noisy. This paper presents a novel unsupervised deep learning architecture for multivariate time series anomaly detection, called Robust Seasonal Multivariate Generative Adversarial Network (RSM-GAN). It extends recent advancements in GANs with adoption of convolutional-LSTM layers and an attention mechanism to produce state-of-the-art performance. We conduct extensive experiments to demonstrate the strength of our architecture in adjusting for complex seasonality patterns and handling severe levels of training data contamination. We also propose a novel anomaly score assignment and causal inference framework. We compare RSM-GAN with existing classical and deep-learning based anomaly detection models, and the results show that our architecture is associated with the lowest false positive rate and improves precision by 30% and 16% in real-world and synthetic data, respectively. Furthermore, we report the superiority of RSM-GAN regarding accurate root cause identification and NAB scores in all data settings.

Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most users are willing to contribute only their encrypted data, and lack interests or resources to join the training of DNNs in cloud. T o train a DNN on encrypted data in a completely non-interactive way, a recent work proposes a fully homomorphic encryption (FHE)-based technique implementing all activations in the neural network by Brakerski-Gentry-V aikuntanathan (BGV)-based lookup tables. However, such inefficient lookup-table-based activations significantly prolong the training latency of privacy-preserving DNNs. In this paper, we propose, Glyph, a FHE-based scheme to fast and accurately train DNNs on encrypted data by switching between TFHE (Fast Fully Homomorphic Encryption over the T orus) and BGV cryptosystems. Glyph uses logic-operation-friendly TFHE to implement nonlinear activations, while adopts vectorial-arithmetic-friendly BGV to perform multiply-accumulation (MAC) operations. Glyph further applies transfer learning on the training of DNNs to improve the test accuracy and reduce the number of MAC operations between ciphertext and ciphertext in convolutional layers. Our experimental results show Glyph obtains the state-of-the-art test accuracy, but reduces the training latency by 99% over the prior FHE-based technique on various encrypted datasets.