Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions. Although tremendous empirical successes have been achieved, most sparse deep learning algorithms are lacking of theoretical support. On the other hand, another line of works have proposed theoretical frameworks that are computationally infeasible. In this paper, we train sparse deep neural networks with a fully Bayesian treatment under spike-and-slab priors, and develop a set of computationally efficient variational inferences via continuous relaxation of Bernoulli distribution. The variational posterior contraction rate is provided, which justifies the consistency of the proposed variational Bayes method. Notably, our empirical results demonstrate that this variational procedure provides uncertainty quantification in terms of Bayesian predictive distribution and is also capable to accomplish consistent variable selection by training a sparse multi-layer neural network.

We propose a hierarchical Bayesian recurrent state space model for modeling switching network connectivity in resting state fMRI data. Our model allows us to uncover shared network patterns across disease conditions. We evaluate our method on the ADNI2 dataset by inferring latent state patterns corresponding to altered neural circuits in individuals with Mild Cognitive Impairment (MCI). In addition to states shared across healthy and individuals with MCI, we discover latent states that are predominantly observed in individuals with MCI. Our model outperforms current state of the art deep learning method on ADNI2 dataset.

In the case of clustered data, an artificial neural network with logcosh loss function learns the bigger cluster rather than the mean of the two. Even more so, the ANN when used for regression of a set-valued function, will learn a value close to one of the choices, in other words, it learns one branch of the set-valued function with high accuracy. This work suggests a method that uses artificial neural networks with logcosh loss to find the branches of set-valued mappings in parameter-outcome sample sets and classifies the samples according to those branches. The method not only classifies the data based on these branches but also provides an accurate prediction for the majority cluster. The method successfully classifies the data based on an invisible feature. A neural network was successfully established to predict the total number of cases, the logarithmic total number of cases, deaths, active cases and other relevant data of the coronavirus for each German district from a number of input variables. As it has been speculated that the Tuberculosis vaccine provides protection against the virus and since East Germany was vaccinated before reunification, an attempt was made to classify the Eastern and Western German districts by considering the vaccine information as an invisible feature.

Except it uses something like the R6 class system and is more "Pythonic" anyways. I wish there were more ways to do DL without having to learn OOP, so that its more accessible for non-programmers. Seems like Keras/TF 2 are still easier if you don't come from that type of background of using OOP heavily. They can be used in R too (though its a wrapper for Python) and the % % in R sort of lets you do it in a more functional "tidy" way. Other than that the only non OOP framework I have seen would be Julia's Flux but its hardly used much.

Google has one of the largest machine learning stacks in the industry, currently centering on its Google Cloud AI and Machine Learning Platform. Google spun out TensorFlow as open source years ago, but TensorFlow is still the most mature and widely cited deep learning framework. Similarly, Google spun out Kubernetes as open source years ago, but it is still the dominant container management system. Google is one of the top sources of tools and infrastructure for developers, data scientists, and machine learning experts, but historically Google AI hasn't been all that attractive to business analysts who lack serious data science or programming backgrounds. The Google Cloud AI and Machine Learning Platform includes AI building blocks, the AI platform and accelerators, and AI solutions.

Some classification techniques such as bagging, cascade learning and AdaBoost were used in region classification step, leading to improvements in detection.

When a hardware-related system disruption like an outage due to hard drive failure happens, the path to recovery includes checking hardware support information, describing the problem to a support representative, waiting for a field technician to arrive, hoping the technician can resolve the issue in a timely manner. Our team of researchers recently published paper "Fine-Grained Visual Recognition in Mobile Augmented Reality for Technical Support," in IEEE ISMAR 2020[1, 2], which outlines an augmented reality (AR) solution that our colleagues in IBM Technology Support Services (TSS) use to increase the rate of first-time fixes and reduce the mean time to recovery from a hardware disruption. "The most recent industry surveys have shown that the average enterprise estimates that there is an impact of approximately $8,851 for every minute of unplanned downtime in their primary computing environment." By displaying guidance over the physical environment, augmented reality support uses visual guidance to drastically reduce the effort needed to relay instructions, the number of errors and even the time required to look up service information. Technical support service providers typically maintain tens of thousands of products in order to meet the needs of their clients.

Many real-world problems require complex coordination between multiple agents -- e.g., people or algorithms. A machine learning technique called multi-agent reinforcement learning (MARL) has shown success with respect to this, mainly in two-team games like Go, DOTA 2, Starcraft, hide-and-seek, and capture the flag. But the human world is far messier than games. That's because humans face social dilemmas at multiple scales, from the interpersonal to the international, and they must decide not only how to cooperate but when to cooperate. To address this challenge, researchers at OpenAI propose training AI agents with what they call randomized uncertain social preferences (RUSP), an augmentation that expands the distribution of environments in which reinforcement learning agents train.

Traditionally recurrent neural networks and their variants have been used extensively for Natural Language Processing problems. In recent years, transformers have outperformed most RNN models. Before looking at transformers, let's revisit recurrent neural networks, how they work, and where they fall behind. There are different types of recurrent neural networks. When it comes to natural language processing RNNs, they work in an encoder-decoder architecture. Encoders will summarize all the information from the input sentence, and the decoder will use the encoder's output to create the right output.

Perhaps no other technology animates the imagination of defense policymakers and analysts as much as artificial intelligence (AI), or more precisely, a subfield of AI called machine learning. The Pentagon is no exception, with the Trump administration having pushed an AI agenda for the military, including through the creation of a Joint Artificial Intelligence Center (JAIC) in 2018. But while military gains from AI technologies are substantial, the way policymakers involved in military AI hard sell its potential often gives observers pause. Speaking virtually at a think tank event on November 6, JAIC's director Lieutenant General Michael Groen compared the military risks the United States faces today to 1914, when World War I broke out, marking the beginning of industrialized warfare. BreakingDefense quotes Groen as saying that "the Information Age equivalent of… lancers riding into machine guns" is using traditional command and control (C2) systems against an adversary equipped with AI. Groen, a Marine Corps intelligence officer whose tours of duty included Iraq and who became JAIC head on October 1, also pointed out the inefficiency of current processes integrating intelligence to kinetic action, in terms of a persistent lag between collation and analysis and engagement even in asymmetric conflicts.