Human intelligence is able to first learn some basic skills for solving basic problems and then assemble such basic skills into complex skills for solving complex or new problems. For example, the basic skills "dig hole," "put tree," "backfill" and "watering" compose a complex skill "plant a tree". Besides, some basic skills can be reused for solving other problems. For example, the basic skill "dig hole" not only can be used for planting a tree, but also can be used for mining treasures, building a drain, or landfilling. The ability to learn basic skills and reuse them for various tasks is very important for humans because it helps to avoid learning too many skills for solving each individual task, and makes it possible to solve a compositional number of tasks by learning just a few number of basic skills, which saves a considerable amount of memory and computation in the human brain. We believe that machine intelligence should also capture the ability of learning basic skills and reusing them by composing into complex skills. In computer science language, each basic skill is a "module", which is a reusable network of a concrete meaning and performs a specific basic operation. The modules are assembled into a bigger "model" for doing a more complex task. The assembling procedure is adaptive to the input or task, i.e., for a given task, the modules should be assembled into the best model for solving the task. As a result, different inputs or tasks could have different assembled models, which enables Auto-Assembling AI (AAAI). In this work, we propose Modularized Adaptive Neural Architecture Search (MANAS) to demonstrate the above idea. Experiments on different datasets show that the adaptive architecture assembled by MANAS outperforms static global architectures. Further experiments and empirical analysis provide insights to the effectiveness of MANAS.

Training Deep Neural Networks (DNNs) is a widely popular workload in both enterprises and cloud data centers. Existing schedulers for DNN training consider GPU as the dominant resource, and allocate other resources such as CPU and memory proportional to the number of GPUs requested by the job. Unfortunately, these schedulers do not consider the impact of a job's sensitivity to allocation of CPU, memory, and storage resources. In this work, we propose Synergy, a resource-sensitive scheduler for shared GPU clusters. Synergy infers the sensitivity of DNNs to different resources using optimistic profiling; some jobs might benefit from more than the GPU-proportional allocation and some jobs might not be affected by less than GPU-proportional allocation. Synergy performs such multi-resource workload-aware assignments across a set of jobs scheduled on shared multi-tenant clusters using a new near-optimal online algorithm. Our experiments show that workload-aware CPU and memory allocations can improve average JCT up to 3.4x when compared to traditional GPU-proportional scheduling.

Network alignment (NA) is the task of discovering node correspondences across different networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their satisfactory performance is not without prior anchor link information and/or node attributes, which may not always be available. In this paper, we propose Grad-Align+, a novel NA method using node attribute augmentation that is quite robust to the absence of such additional information. Grad-Align+ is built upon a recent state-of-the-art NA method, the so-called Grad-Align, that gradually discovers only a part of node pairs until all node pairs are found. Specifically, Grad-Align+ is composed of the following key components: 1) augmenting node attributes based on nodes' centrality measures, 2) calculating an embedding similarity matrix extracted from a graph neural network into which the augmented node attributes are fed, and 3) gradually discovering node pairs by calculating similarities between cross-network nodes with respect to the aligned cross-network neighbor-pair. Experimental results demonstrate that Grad-Align+ exhibits (a) superiority over benchmark NA methods, (b) empirical validation of our theoretical findings, and (c) the effectiveness of our attribute augmentation module.

Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process, today's language models are trained to generate only the final result. As a consequence, they lack several abilities crucial for collaborative writing: They are unable to update existing texts, difficult to control and incapable of verbally planning or explaining their actions. To address these shortcomings, we introduce PEER, a collaborative language model that is trained to imitate the entire writing process itself: PEER can write drafts, add suggestions, propose edits and provide explanations for its actions. Crucially, we train multiple instances of PEER able to infill various parts of the writing process, enabling the use of self-training techniques for increasing the quality, amount and diversity of training data. This unlocks PEER's full potential by making it applicable in domains for which no edit histories are available and improving its ability to follow instructions, to write useful comments, and to explain its actions. We show that PEER achieves strong performance across various domains and editing tasks.

When humans work together to complete a joint task, each person builds an internal model of the situation and how it will evolve. Efficient collaboration is dependent on how these individual models overlap to form a shared mental model among team members, which is important for collaborative processes in human-robot teams. The development and maintenance of an accurate shared mental model requires bidirectional communication of individual intent and the ability to interpret the intent of other team members. To enable effective human-robot collaboration, this paper presents a design and implementation of a novel joint action framework in human-robot team collaboration, utilizing augmented reality (AR) technology and user eye gaze to enable bidirectional communication of intent. We tested our new framework through a user study with 37 participants, and found that our system improves task efficiency, trust, as well as task fluency. Therefore, using AR and eye gaze to enable bidirectional communication is a promising mean to improve core components that influence collaboration between humans and robots.

The wide spread of false information online including misinformation and disinformation has become a major problem for our highly digitised and globalised society. A lot of research has been done to better understand different aspects of false information online such as behaviours of different actors and patterns of spreading, and also on better detection and prevention of such information using technical and socio-technical means. One major approach to detect and debunk false information online is to use human fact-checkers, who can be helped by automated tools. Despite a lot of research done, we noticed a significant gap on the lack of conceptual models describing the complicated ecosystems of false information and fact checking. In this paper, we report the first graphical models of such ecosystems, focusing on false information online in multiple contexts, including traditional media outlets and user-generated content. The proposed models cover a wide range of entity types and relationships, and can be a new useful tool for researchers and practitioners to study false information online and the effects of fact checking.

Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restriction by predicting classes based on adaptable class descriptions. This study sets out to investigate the effectiveness of self-attention-based audio embedding architectures for ZS learning. To this end, we compare the very recent patchout spectrogram transformer with two classic convolutional architectures. We evaluate these three architectures on three tasks and on three different benchmark datasets: general-purpose tagging on AudioSet, environmental sound classification on ESC-50, and instrument tagging on OpenMIC. Our results show that the self-attention-based embedding methods outperform both compared convolutional architectures in all of these settings. By designing training and test data accordingly, we observe that prediction performance suffers significantly when the `semantic distance' between training and new test classes is large, an effect that will deserve more detailed investigations.

I found the book quite didactic and entertaining. Theano and Tensorflow are explored briefly in some specific chapters at the beginning of the book, but most of the material covers how to use Keras effectively with CNNs and RNNs. I found the Time Series and model improvement chapters specially interesting. I recommend this book for newbies willing to get a soft landing into Deep Learning with Python&Keras. I think this is Jason's best book to date. Starting with no previous deep learning experience and little familiarity with Python, over the course of a weekend I was able to develop and train a Convolutional Neural Net that achieved a 0.8% error rate on the famous MNIST digit recognition task (best-in-class is 0.23%). If you're struggling to get up to speed with deep learning, this book is a great way to get started.

With recent advances in brain implants touted by the likes of Elon Musk, mind-altering technology might not be the stuff of science fiction for much longer. Neurotechnologies are brain implants or pieces of wearable tech that interact directly with the brain by monitoring or influencing neural activity. They are already being used in medicine to treat Parkinson's disease and tested by military organisations looking to employ'cyborg soldiers'. A report published this month by lawyer Dr Allan McCay from Sydney University looked at the ways the legal profession could change if implants become more mainstream in society. It suggests that law enforcement agencies could utilise brain chips in order to manage the behaviour of the convicted and help prevent re-offending.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses.