Recent backscatter communication techniques enable ultra low power wireless devices that operate without batteries while interoperating directly with unmodified commodity wireless devices. Commodity devices cooperate in providing the unmodulated carrier that the battery-free nodes need to communicate while collecting energy from their environment to perform sensing, computation, and communication tasks. The optimal provision of the unmodulated carrier limits the size of the network because it is an NP-hard combinatorial optimization problem. Consequently, previous works either ignore carrier optimization altogether or resort to suboptimal heuristics, wasting valuable energy and spectral resources. We present DeepGANTT, a deep learning scheduler for battery-free devices interoperating with wireless commodity ones. DeepGANTT leverages graph neural networks to overcome variable input and output size challenges inherent to this problem. We train our deep learning scheduler with optimal schedules of relatively small size obtained from a constraint optimization solver. DeepGANTT not only outperforms a carefully crafted heuristic solution but also performs within ~3% of the optimal scheduler on trained problem sizes. Finally, DeepGANTT generalizes to problems more than four times larger than the maximum used for training, therefore breaking the scalability limitations of the optimal scheduler and paving the way for more efficient backscatter networks.

Clearview AI has been provided with the go-ahead signal for securing a federal patent for its facial recognition software, as reported by Politico. The US Patents and Trademarks Office sent a "notice of allowance" to Clearview on December 1, implying that the patent will be awarded once the organization pays the necessary administrative fees. The patent will, among other things, cover its method of obtaining information, specifically, its "automated web crawler" tool that scans social networking sites and the internet, the same process that has led the company to face extensive backlash from numerous privacy advocates. "There are other facial recognition patents out there -- that are methods of doing it -- but this is the first one around the use of large-scale internet data," Ton-That, the founder of Clearview AI, told Politico in an interview. Clearview AI has more than 10 billion photos in their database, which was confirmed by Ton-That, much more than the previous estimate of 3 billion images.

Artificial intelligence (AI) backed drug discovery company Insilico Medicine announced last week that it was dosing the first healthy volunteer in a microdose trial of ISM 001-005. Designed with the help of AI, the drug is a small-molecule inhibitor of a biological target that was discovered by Pharma.AI. The trial is being conducted in Australia. The AI-designed drug will be used to treat chronic lung disease idiopathic pulmonary fibrosis, or IPF. IPF usually leads to progressive and irreversible lung-function decline and affects 20 people out of over 100,000 globally.

Modern neural language models widely used in tasks across NLP risk memorizing sensitive information from their training data. As models continue to scale up in parameters, training data, and compute, understanding memorization in language models is both important from a learning-theoretical point of view, and is practically crucial in real world applications. An open question in previous studies of memorization in language models is how to filter out "common" memorization. In fact, most memorization criteria strongly correlate with the number of occurrences in the training set, capturing "common" memorization such as familiar phrases, public knowledge or templated texts. In this paper, we provide a principled perspective inspired by a taxonomy of human memory in Psychology. From this perspective, we formulate a notion of counterfactual memorization, which characterizes how a model's predictions change if a particular document is omitted during training. We identify and study counterfactually-memorized training examples in standard text datasets. We further estimate the influence of each training example on the validation set and on generated texts, and show that this can provide direct evidence of the source of memorization at test time.

The disruption of supplies during the Covid-19 crisis has led to shortages but has also shown the adaptability of some companies, which have succeeded in adapting their production chains quickly to produce goods experiencing shortages: hydroalcoholic gel, masks, and medical gowns. These productive jumps from product A to product B are feasible because of the know-how proximity between the two classes of products. The proximities were computed from the analysis of co-exports and resulted in the construction of the product space. Based on the product space, as well as the customer-supplier relationships resulting from the input-output matrices, we propose a recommender system for companies. The goal is to promote distributed manufacturing by recommending a list of local suppliers to each company. As there is not always a local supplier for a desired product class, we consider the proximity between products to identify, in the absence of a supplier, a substitute supplier able to adapt its production tools to provide the required product. Our experiments are based on French data, from which we build a graph of synergies illustrating the potential productive links between companies. Finally, we show that our approach offers new perspectives to determine the level of territories' industrial resilience considering potential productive jumps.

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual semantics within and between character instances, making them not generalize well to arbitrary shape scene text. To address this issue, we make the first attempt to perform textual reasoning based on visual semantics in this paper. Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity. Then, these subgraphs are sequentially connected by their root nodes and merged into a complete graph. Based on this graph, we devise a graph convolutional network for textual reasoning (GTR) by supervising it with a cross-entropy loss. GTR can be easily plugged in representative STR models to improve their performance owing to better textual reasoning. Specifically, we construct our model, namely S-GTR, by paralleling GTR to the language model in a segmentation-based STR baseline, which can effectively exploit the visual-linguistic complementarity via mutual learning. S-GTR sets new state-of-the-art on six challenging STR benchmarks and generalizes well to multi-linguistic datasets. Code is available at https://github.com/adeline-cs/GTR.

Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream," specialized datasets. Generally, it is understood that more accurate models on the "upstream" dataset will provide better transfer accuracy "downstream". In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned - that is, compressed by sparsifiying their connections. Specifically, we consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, re-growth and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods.

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving human control over complex tasks, are a good trade-off to speed up image labeling while maintaining high accuracy levels. TagLab is an open-source AI-assisted software for annotating large orthoimages which takes advantage of different degrees of automation; it speeds up image annotation from scratch through assisted tools, creates custom fully automatic semantic segmentation models, and, finally, allows the quick edits of automatic predictions. Since the orthoimages analysis applies to several scientific disciplines, TagLab has been designed with a flexible labeling pipeline. We report our results in two different scenarios, marine ecology, and architectural heritage.

The EU has concluded Microsoft's $19.7 billion acquisition of Nuance doesn't pose competition concerns. Nuance gained renown for originally creating the backend of that little old virtual assistant called Siri (you might have heard of it?) The company has since continued to focus on building its speech recognition capabilities and has a number of solutions which span particular industries such as healthcare to general omni-channel customer experience services. Earlier this year, Microsoft decided Nuance is worth coughing up $19.7 billion for. As such large deals often do, the proposed acquisition caught the eyes of several global regulators.

Disruptive technology is the technology that affects the normal operation of a market or an industry. Digital disruption entails established companies and start-ups alike enlisting new technologies in the fight to dislodge incumbents, protect entrenched positions, or to re-invent entire industries and business activities. And to remain disruptive in the market, it is really important to keep innovating. This is crucial because, innovations occur now and then in every industry, however, to be truly disruptive, and innovation must entirely transform a product or solution that historically was so complicated only a few could access it. On a minimum level, digital transformation enables an organization to address the needs of its customers more simply and directly. But through disruptive innovation, companies can offer a far better way to users of doing things that current incumbents simply cannot compete with. Artificial intelligence (AI), E-Commerce, cloud, social networking, Internet of Things, 5G, blockchain and other emerging technologies are being leveraged to blur the lines between industries, creating new business models and converging sectors. A company that disrupts its market is in a great position to take advantage of new opportunities. Sometimes offering something different can change the whole market for the better. Most of the top disruptive companies get this label by offering highly innovative products and services and here are 100 such top disruptive companies listed below. The company provides innovative, managed cloud services to help its customers succeed. With best-in-class service and technology, 403Tech protects companies against cybercrimes while enabling greater efficiency and productivity. Some of its popular services include desktop support, server support, wired and wireless networking, virus removal, data recovery, and backup and hosted cloud services. Aegeus Technologies aims to design and develop robotic technologies and solutions.