Artificial intelligence (AI) is used by medical facilities to help analyze x-rays and other medical scans, but a new study finds the technology can see more than just a patient's health – it can determine their race with startling accuracy. The study's 20 authors found deep learning models can identify race in chest and hand x-rays and mammograms among patients who identified as black, white and Asian. The algorithms correctly identify which images were from a black person more than 90 percent of the time, but also showed it was able to identity race with 99 percent accuracy at times. However, what is even more alarming is that the team was unable to explain how the AI systems were making accurate predictions, some of which were done with scans that were blurry or low-resolution. 'We emphasize that model ability to predict self-reported race is itself not the issue of importance,' Ritu Banerjee, associate professor of pediatrics at Washington University School of Medicine and lead author of the study, and collages wrote in the study published in arXiv.

Humans do not start learning everything from the beginning; they basically relate the things to each other to make inferences about the new thing in their mind. For example, when they learn how to ride a motorcycle and they already know how to cycle, they don't need to learn about braking or any other basic things because they already know them. Traditional neural networks can't do this. They are networks with various loops to persist the information and LSTM(long short term memory) are a special kind of recurrent neural networks. Which are very useful when dealing with sequential data like time series data and NLP data.

Engineering trust, accelerating growth and sculpting change are the three predominant trends Gartner has selected for its Hype Cycle for Emerging Technologies, 2021. They will drive organizations to explore emerging technologies such as nonfungible tokens (NFT), sovereign cloud, data fabric, generative AI and composable networks to help secure competitive advantage, the research firm said. Gartner's hype cycle provides a high-level view of important emerging trends that organizations must track, along with the specific technologies that must be monitored through the themes of trust, growth and change, said Philip Dawson, research vice president at Gartner. Engineering Trust: Trust demands security and reliability, Gartner said. However, it can also extend to building innovations as a resilient core and foundation for IT to deliver business value.

We already observe the importance and the ability of the artificial neural networks to do the intensive tasks particularly on the computer vision or the natural language processing fields in these recent years. However, it is known that far more researches still need to be implemented for the automations on human tasks via deep learning. For instances, we may ask ourselves is it possible for us to utilize deep learning to create something new or things that are not existed. Is it possible for us to use deep learning to generate or create artworks with similar styles but different contents by learning from the painter's past works? These tasks sound to be difficult but GANs make it possible!

Nonfungible tokens (NFT) have 2 to 5 years before plateauing after hitting a "trough of disillusionment" and active metadata management, composable applications and generative AI are in the same camp, according to Gartner's 2021 Hype Cycle for Emerging Technologies. Now the hype cycle report from Gartner is always good for debate. But the hype cycle is even better for tech buyers who need to know what buzzword bingo they're about to receive from vendors. Gartner's emerging technology hype cycle distills more than 1,500 technologies into a list of must know tools. Also: What is quantum computing?

This book develops an effective theory approach to understanding deep neural networks of practical relevance. Beginning from a first-principles component-level picture of networks, we explain how to determine an accurate description of the output of trained networks by solving layer-to-layer iteration equations and nonlinear learning dynamics. A main result is that the predictions of networks are described by nearly-Gaussian distributions, with the depth-to-width aspect ratio of the network controlling the deviations from the infinite-width Gaussian description. We explain how these effectively-deep networks learn nontrivial representations from training and more broadly analyze the mechanism of representation learning for nonlinear models. From a nearly-kernel-methods perspective, we find that the dependence of such models' predictions on the underlying learning algorithm can be expressed in a simple and universal way. To obtain these results, we develop the notion of representation group flow (RG flow) to characterize the propagation of signals through the network. By tuning networks to criticality, we give a practical solution to the exploding and vanishing gradient problem. We further explain how RG flow leads to near-universal behavior and lets us categorize networks built from different activation functions into universality classes. Altogether, we show that the depth-to-width ratio governs the effective model complexity of the ensemble of trained networks. By using information-theoretic techniques, we estimate the optimal aspect ratio at which we expect the network to be practically most useful and show how residual connections can be used to push this scale to arbitrary depths. With these tools, we can learn in detail about the inductive bias of architectures, hyperparameters, and optimizers.

The automatic detection of humor poses a grand challenge for natural language processing. Transformer-based systems have recently achieved remarkable results on this task, but they usually (1)~were evaluated in setups where serious vs humorous texts came from entirely different sources, and (2)~focused on benchmarking performance without providing insights into how the models work. We make progress in both respects by training and analyzing transformer-based humor recognition models on a recently introduced dataset consisting of minimal pairs of aligned sentences, one serious, the other humorous. We find that, although our aligned dataset is much harder than previous datasets, transformer-based models recognize the humorous sentence in an aligned pair with high accuracy (78%). In a careful error analysis, we characterize easy vs hard instances. Finally, by analyzing attention weights, we obtain important insights into the mechanisms by which transformers recognize humor. Most remarkably, we find clear evidence that one single attention head learns to recognize the words that make a test sentence humorous, even without access to this information at training time.

This paper aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial-temporal dependencies for spatial-temporal graph data. For spatial-temporal attribute entities with topological structure, the space-time is consecutive and unified while each node's current status is influenced by its neighbors' past states over variant periods of each neighbor. Most spatial-temporal neural networks study spatial dependency and temporal correlation separately in processing, gravely impaired the space-time continuum, and ignore the fact that the neighbors' temporal dependency period for a node can be delayed and dynamic. To model this actual condition, we propose TraverseNet, a novel spatial-temporal graph neural network, viewing space and time as an inseparable whole, to mine spatial-temporal graphs while exploiting the evolving spatial-temporal dependencies for each node via message traverse mechanisms. Experiments with ablation and parameter studies have validated the effectiveness of the proposed TraverseNets, and the detailed implementation can be found from https://github.com/nnzhan/TraverseNet.

Sketches are a medium to convey a visual scene from an individual's creative perspective. The addition of color substantially enhances the overall expressivity of a sketch. This paper proposes two methods to mimic human-drawn colored sketches by utilizing the Contour Drawing Dataset. Our first approach renders colored outline sketches by applying image processing techniques aided by k-means color clustering. The second method uses a generative adversarial network to develop a model that can generate colored sketches from previously unobserved images. We assess the results obtained through quantitative and qualitative evaluations.

It is fundamental for personal robots to reliably navigate to a specified goal. To study this task, PointGoal navigation has been introduced in simulated Embodied AI environments. Recent advances solve this PointGoal navigation task with near-perfect accuracy (99.6% success) in photo-realistically simulated environments, assuming noiseless egocentric vision, noiseless actuation, and most importantly, perfect localization. However, under realistic noise models for visual sensors and actuation, and without access to a "GPS and Compass sensor," the 99.6%-success agents for PointGoal navigation only succeed with 0.3%. In this work, we demonstrate the surprising effectiveness of visual odometry for the task of PointGoal navigation in this realistic setting, i.e., with realistic noise models for perception and actuation and without access to GPS and Compass sensors. We show that integrating visual odometry techniques into navigation policies improves the state-of-the-art on the popular Habitat PointNav benchmark by a large margin, improving success from 64.5% to 71.7% while executing 6.4 times faster.