Intel is sponsoring an online course to help address the shortage of AIoT developers... Amid rapid growth in AI deployments across a variety of industry sectors, Intel has decided to address the skills shortage in AI-savvy developers by partnering with online technology learning platform Udacity to offer a course in edge AI for developers. "Historically, students have learned how to build and deploy deep learning models for the cloud. With Udacity, we are training AI developers to go where the data is generated in the physical world: the edge," said Jonathan Ballon, Intel vice president and general manager, Internet of Things Group. "Optimizing direct deployment of models on edge devices requires knowledge of unique constraints like power, network bandwidth and latency, varying compute architectures and more. The skills this course delivers will allow developers -- and companies that hire them, to implement learnings on real-world applications across a variety of fields."

One of the goals of AI research is to teach machines how to do the same things people do, but better. In the early 2000s, this meant focusing on problems like flying helicopters and walking up flights of stairs. However, there's still a massive list of problems where humans outperform machines. Although we can no longer claim to beat machines at tasks like Go and image classification, we have a distinct advantage in solving problems that aren't as well-defined, like judging a well-executed backflip, cleaning a room while preventing accidents, and perhaps the most human problem of all: reasoning about people's values. Since all these tasks contain some degree of subjectivity, machines need information about the world as well as a way to learn about the people within it in order to solve these problems.

From developing drug treatments to predicting the next hotspot, artificial intelligence may help researchers, healthcare workers, and everyday people offset the impact of the coronavirus. As the worldwide fight against coronavirus COVID-19 continues, companies and governments around the world are pulling out all the stops in an effort to stave off the pandemic's worst impacts. One tool in that toolbox that might prove particularly useful is artificial intelligence (AI). Even though AI has been around since the 1960s, it's only been in the past few years that its adoption outside of science labs and research institutions has really taken off. Perhaps the most common application of AI people have come into contact with today are virtual assistants like Apple's Siri and Amazon's Alexa, which rely on natural language processing (NLP) algorithms to understand human speech.

The AI engine supports a self-operating building that requires no human intervention. What inspired you to launch BrainBox AI? My journey into HVAC technology began while working on energy efficiency projects throughout North America and Europe. During this stage of my life, I dealt with the technology in a plethora of buildings. These were buildings of different sizes and purpose, anything from hotels all the way to data centers. It quickly became apparent to me that continuous commissioning approaches would generate consistent energy savings but would require extensive amounts of both financial and human capital.

In this paper, we deal with the problem of automatic tag recommendation for painting artworks. Diachronic descriptions containing deviations on the vocabulary used to describe each painting usually occur when the work is done by many experts over time. The objective of this work is to provide a framework that produces a more accurate and homogeneous set of tags for each painting in a large collection. To validate our method we build a model based on a weakly-supervised neural network for over $5{,}300$ paintings with hand-labeled descriptions made by experts for the paintings of the Brazilian painter Candido Portinari. This work takes place with the Portinari Project which started in 1979 intending to recover and catalog the paintings of the Brazilian painter. The Portinari paintings at that time were in private collections and museums spread around the world and thus inaccessible to the public. The descriptions of each painting were made by a large number of collaborators over 40 years as the paintings were recovered and these diachronic descriptions caused deviations on the vocabulary used to describe each painting. Our proposed framework consists of (i) a neural network that receives as input the image of each painting and uses frequent itemsets as possible tags, and (ii) a clustering step in which we group related tags based on the output of the pre-trained classifiers.

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges. Typical learnable quantization schemes [PACT, LSQ] assume unsigned quantization for activations and quantize all negative activations to zero which leads to significant loss in performance. Naively using signed quantization to accommodate these negative values requires an extra sign bit which is expensive for low-bit (2-, 3-, 4-bit) quantization. To solve this problem, we propose LSQ+, a natural extension of LSQ, wherein we introduce a general asymmetric quantization scheme with trainable scale and offset parameters that can learn to accommodate the negative activations. Gradient-based learnable quantization schemes also commonly suffer from high instability or variance in the final training performance, hence requiring a great deal of hyper-parameter tuning to reach a satisfactory performance. LSQ+ alleviates this problem by using an MSE-based initialization scheme for the quantization parameters. We show that this initialization leads to significantly lower variance in final performance across multiple training runs. Overall, LSQ+ shows state-of-the-art results for EfficientNet and MixNet and also significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations (e.g.: 1.8% gain with W4A4 quantization and upto 5.6% gain with W2A2 quantization of EfficientNet-B0 on ImageNet dataset). To the best of our knowledge, ours is the first work to quantize such architectures to extremely low bit-widths.

Discovery of causal relationships from observational data is an important problem in many areas. Several recent results have established the identifiability of causal DAGs with non-Gaussian and/or nonlinear structural equation models (SEMs). In this paper, we focus on nonlinear SEMs defined by non-invertible functions, which exist in many data domains, and propose a novel test for non-invertible bivariate causal models. We further develop a method to incorporate this test in structure learning of DAGs that contain both linear and nonlinear causal relations. By extensive numerical comparisons, we show that our algorithms outperform existing DAG learning methods in identifying causal graphical structures. We illustrate the practical application of our method in learning causal networks for combinatorial binding of transcription factors from ChIP-Seq data.

The latest work for Question and Answer problems is to use the Stanford Parse Tree. We build on prior work and develop a new method to handle the Question and Answer problem with the Deep Contextualized Transformer to manage some aberrant expressions. We also conduct extensive evaluations of the SQuAD and SwDA dataset and show significant improvement over QA problem classification of industry needs. We also investigate the impact of different models for the accuracy and efficiency of the problem answers. It shows that our new method is more effective for solving QA problems with higher accuracy

Facial sketches drawn by artists are widely used for visual identification applications and mostly by law enforcement agencies, but the quality of these sketches depend on the ability of the artist to clearly replicate all the key facial features that could aid in capturing the true identity of a subject. Recent works have attempted to synthesize these sketches into plausible visual images to improve visual recognition and identification. However, synthesizing photo-realistic images from sketches proves to be an even more challenging task, especially for sensitive applications such as suspect identification. In this work, we propose a novel approach that adopts a generative adversarial network that synthesizes a single sketch into multiple synthetic images with unique attributes like hair color, sex, etc. We incorporate a hybrid discriminator which performs attribute classification of multiple target attributes, a quality guided encoder that minimizes the perceptual dissimilarity of the latent space embedding of the synthesized and real image at different layers in the network and an identity preserving network that maintains the identity of the synthesised image throughout the training process. Our approach is aimed at improving the visual appeal of the synthesised images while incorporating multiple attribute assignment to the generator without compromising the identity of the synthesised image. We synthesised sketches using XDOG filter for the CelebA, WVU Multi-modal and CelebA-HQ datasets and from an auxiliary generator trained on sketches from CUHK, IIT-D and FERET datasets. Our results are impressive compared to current state of the art.

An autoencoder is a layered neural network whose structure can be viewed as consisting of an encoder, which compresses an input vector of dimension $D$ to a vector of low dimension $d$, and a decoder which transforms the low-dimensional vector back to the original input vector (or one that is very similar). In this paper we explore the compressive power of autoencoders that are Boolean threshold networks by studying the numbers of nodes and layers that are required to ensure that the numbers of nodes and layers that are required to ensure that each vector in a given set of distinct input binary vectors is transformed back to its original. We show that for any set of $n$ distinct vectors there exists a seven-layer autoencoder with the smallest possible middle layer, (i.e., its size is logarithmic in $n$), but that there is a set of $n$ vectors for which there is no three-layer autoencoder with a middle layer of the same size. In addition we present a kind of trade-off: if a considerably larger middle layer is permissible then a five-layer autoencoder does exist. We also study encoding by itself. The results we obtain suggest that it is the decoding that constitutes the bottleneck of autoencoding. For example, there always is a three-layer Boolean threshold encoder that compresses $n$ vectors into a dimension that is reduced to twice the logarithm of $n$.