FREMONT, CA- Artificial Intelligence has come a long way, and it is here to stay.

In March 2016, Microsoft sent its artificial intelligence (AI) bot Tay out into the wild to see how it interacted with humans. According to Microsoft Cybersecurity Field CTO Diana Kelley, the team behind Tay wanted the bot to pick up natural language and thought Twitter was the best place for it to go. "A great example of AI and ML going awry is Tay," Kelley told RSA Conference 2019 Asia Pacific and Japan in Singapore last week. Tay was targeted at American 18 to 24-year olds and was "designed to engage and entertain people where they connect with each other online through casual and playful conversation". Here's how it's related to artificial intelligence, how it works and why it matters.

IBM recently developed three artificial intelligence tools that could help medical researchers fight cancer. Now, the company has decided to make all three tools open-source, meaning scientists will be able to use them in their research whenever they please, according to ZDNet. The tools are designed to streamline the cancer drug development process and help scientists stay on top of newly-published research -- so, if they prove useful, it could mean more cancer treatments coming through the pipeline more rapidly than before. This week, IBM scientists are presenting the three AI tools at two molecular biology conferences in Switzerland, according to an IBM press release. The first, PaccMann, uses deep learning algorithms to predict whether compounds will be viable anticancer drugs, taking some of the expensive guesswork out of pharmaceutical development, according to the press release.

Only early adopter corporate executives with a better than average understanding of the AI/ML cognitive processes have whole heartedly embraced AI/ML implementation across the enterprise. The majority of the rest of corporate executives are evaluating AI/ML in baby steps measuring risk vs. return. Following those executives and measuring AI/ML concerns and prospective adoption are top data analyst organizations like Deloitte, McKinsey, PricewaterhouseCoopers (PWC), Forrester and IDC. Surveys have shown that during early stages of AI/ML development, there was a rush to implement across the whole enterprise. Recently, adoption has slowed with executives beginning AI/ML pilots in predictable successful segments of their operations.

There are positive uses for deepfake technology like making digital voices for people who lost theirs or updating film footage instead of reshooting it if actors trip over their lines. However, the potential for malicious use is of grave concern, especially as the technology gets more refined. There has been tremendous progress in the quality of deepfakes since only a few years ago when the first products of the technology circulated. Since that time, many of the scariest examples of artificial intelligence (AI)-enabled deepfakes have technology leaders, governments, and media talking about the perils it could create for communities. The first exposure to deepfakes for most of the general public happened in 2017.

The federal business watchdog will reportedly find that Facebook deceived users about how it handled phone numbers it asked for as part of a security feature and provided insufficient information about how to turn off a facial recognition tool for photos.

Evidence continues to mount that facial recognition systems - some of which are already deployed by police forces worldwide - struggle to tell black people apart. Research conducted by the National Institute of Standards and Technology (NIST) in the US tested AI software from more than 50 companies across the globe. Experts from the government agency found up to a tenfold difference in error rate when it came to correctly identifying black women compared to white females. White men were found to present the least challenge when it came to correct identification. The finding builds on previous studies that have also noted serious discrepancies in facial recognition tools when it comes to images of people with darker skin tones.

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the measure and running non-convex gradient descent on the positions and weights of the particles. For measures on a $d$-dimensional manifold and under some non-degeneracy assumptions, this leads to a global optimization algorithm with a complexity scaling as $\log(1/\epsilon)$ in the desired accuracy $\epsilon$, instead of $\epsilon^{-d}$ for convex methods. The key theoretical tools are a local convergence analysis in Wasserstein space and an analysis of a perturbed mirror descent in the space of measures. Our bounds involve quantities that are exponential in $d$ which is unavoidable under our assumptions.

In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven health monitoring systems is gaining in popularity due to the large availability of data from low-cost sensors with internetworking capabilities. In particular, deep learning provides the tools for processing and analyzing this unprecedented amount of data efficiently. The main purpose of this paper is to combine the recent advances of Deep Learning (DL) and statistical analysis on structural health monitoring (SHM) to develop an accurate classification tool able to discriminate among different acoustic emission events (cracks) by means of the identification of tensile, shear and mixed modes. The applications of DL in SHM systems is described by using the concept of Bidirectional Long Short Term Memory. We investigated on effective event descriptors to capture the unique characteristics from the different types of modes. Among them, Spectral Kurtosis and Spectral L2/L1 Norm exhibit distinctive behavior and effectively contributed to the learning process. This classification will contribute to unambiguously detect incipient damages, which is advantageous to realize predictive maintenance. Tests on experimental results confirm that this method achieves accurate classification (92%) capabilities of crack events and can impact on the design of future SHM technologies.