The lack of adequate training data is one of the major hurdles in WiFi-based activity recognition systems. In this paper, we propose Wi-Fringe, which is a WiFi CSI-based device-free human gesture recognition system that recognizes named gestures, i.e., activities and gestures that have a semantically meaningful name in English language, as opposed to arbitrary free-form gestures. Given a list of activities (only their names in English text), along with zero or more training examples (WiFi CSI values) per activity, Wi-Fringe is able to detect all activities at runtime. In other words, a subset of activities that Wi-Fringe detects do not require any training examples at all.

Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain. Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to $n$ target domains (as long as there is paired data covering all domains). Our multi-domain adaptation method utilises a consistency loss combined with adversarial learning. We provide results on white matter lesion hyperintensity segmentation from brain MRIs using the MICCAI 2017 challenge data as the source domain and two target domains. The proposed method significantly outperforms other domain adaptation baselines.

Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is most uncertain (by some measure). The hope is that active sampling leads to better performance than would be achieved under independent and identically distributed (i.i.d.) random samples. While AL has shown promise in retrospective evaluations, these studies often ignore practical obstacles to its use. In this paper we show that while AL may provide benefits when used with specific models and for particular domains, the benefits of current approaches do not generalize reliably across models and tasks. This is problematic because in practice one does not have the opportunity to explore and compare alternative AL strategies. Moreover, AL couples the training dataset with the model used to guide its acquisition. We find that subsequently training a successor model with an actively-acquired dataset does not consistently outperform training on i.i.d. sampled data. Our findings raise the question of whether the downsides inherent to AL are worth the modest and inconsistent performance gains it tends to afford.

Nvidia says it's achieved significant advances in conversation natural language processing (NLP) training and inference, enabling more complex, immediate-response interchanges between customers and chatbots. And the company says it has a new language training model in the works that dwarfs existing ones. Nvidia said its DGX-2 AI platform trained the BERT-Large AI language model in less than an hour and performed AI inference in 2 milliseconds making "it possible for developers to use state-of-the-art language understanding for large-scale applications…." Training: Running the largest version of Bidirectional Encoder Representations from Transformers (BERT-Large) language model, an Nvidia DGX SuperPOD with 92 Nvidia DGX-2H systems running 1,472 V100 GPUs cut training from several days to 53 minutes. A single DGX-2 system trained BERT-Large in 2.8 days.

We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data. We apply it to the Semantic Image Interpretation (SII) task and show that background knowledge provides significant improvement. We find that there is a strong but interesting imbalance between the contributions of updates from Modus Ponens (MP) and its logical equivalent Modus Tollens (MT) to the learning process, suggesting that our approach is very sensitive to a phenomenon called the Raven Paradox. We propose a solution to overcome this situation.

Everyday robotics are challenged to deal with autonomous product handling in applications like logistics or retail, possibly causing damage on the items during manipulation. Traditionally, most approaches try to minimize physical interaction with goods. However, this paper proposes to take into account any unintended object motion and to learn damage-minimizing manipulation strategies in a self-supervised way. The presented approach consists of a simulation-based planning method for an optimal manipulation sequence with respect to possible damage. The planned manipulation sequences are generalized to new, unseen scenes in the same application scenario using machine learning. This learned manipulation strategy is continuously refined in a self-supervised, simulation-in-the-loop optimization cycle during load-free times of the system, commonly known as mental simulation. In parallel, the generated manipulation strategies can be deployed in near-real time in an anytime fashion. The approach is validated on an industrial container-unloading scenario and on a retail shelf-replenishment scenario.

Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning algorithms employ a heuristic-guided search for rules that model regularities contained in the training data and it is commonly accepted that the choice of the heuristic has a significant impact on the predictive performance of the learner. Whereas the properties of rule learning heuristics have been studied in the realm of single-label classification, there is no such work taking into account the particularities of multi-label classification. This is surprising, as the quality of multi-label predictions is usually assessed in terms of a variety of different, potentially competing, performance measures that cannot all be optimized by a single learner at the same time. In this work, we show empirically that it is crucial to trade off the consistency and coverage of rules differently, depending on which multi-label measure should be optimized by a model. Based on these findings, we emphasize the need for configurable learners that can flexibly use different heuristics. As our experiments reveal, the choice of the heuristic is not straight-forward, because a search for rules that optimize a measure locally does usually not result in a model that maximizes that measure globally.

If you suffered during the recent record-smashing heatwave across Europe, there's bad news. Such heatwaves are the new normal for countries like the UK, and we can expect even more extreme ones in the next few years, say climate scientists who have studied the event. "People say, oh this is historic and this will make history," says Friederike Otto of Oxford University in the UK. "It will probably not make history because we should expect that these records will be broken in the next few years."

Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into fixed-dimensional vectors in a shared latent space; such that the distance between two word vectors represents how closely the two words sound. Instead of directly learning the distances between word vectors, we employ weak supervision and model a binary classification task to predict whether two inputs, one of each modality, represent the same word given a distance threshold. We explore various deep-learning models, bimodal contrastive losses, and techniques for mining hard negative examples such as the semi-supervised technique of self-labeling. Our best model achieves an $F_1$ score of 0.95 for the binary classification task.

--Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm works the best on a particular problem. We believe that the two crucial steps of MCS - base classifier generation and multiple classifier combination, need to be designed coordinately to produce robust results. In this work, we show that for different testing instances, better classifiers may be trained from different subdomains of training instances including, for example, neighboring instances of the testing instance, or even instances far away from the testing instance. T o utilize this intuition, we propose Individualized Classifier Ensemble (ICE). ICE groups training data into overlapping clusters, builds a classifier for each cluster, and then associates each training instance to the top-performing models while taking into account model types and frequency. In testing, ICE finds the k most similar training instances for a testing instance, then predicts class label of the testing instance by averaging the prediction from models associated with these training instances. Evaluation results on 49 benchmarks show that ICE has a stable improvement on a significant proportion of datasets over existing MCS methods. ICE provides a novel choice of utilizing internal patterns among instances to improve classification, and can be easily combined with various classification models and applied to many application domains.