Every AI system is deployed by a human organization. In high risk applications, the combined human plus AI system must function as a high-reliability organization in order to avoid catastrophic errors. This short note reviews the properties of high-reliability organizations and draws implications for the development of AI technology and the safe application of that technology.

Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword. In this work, we present DONUT, a CTC-based algorithm for online query-by-example keyword spotting that enables custom wakeword detection. The algorithm works by recording a small number of training examples from the user, generating a set of label sequence hypotheses from these training examples, and detecting the wakeword by aggregating the scores of all the hypotheses given a new audio recording. Our method combines the generalization and interpretability of CTC-based keyword spotting with the user-adaptation and convenience of a conventional query-by-example system. DONUT has low computational requirements and is well-suited for both learning and inference on embedded systems without requiring private user data to be uploaded to the cloud.

IBM and the other vendors who are bidding on the CORAL2 systems for the US Department of Energy can't talk about those bids, which are in flight, and Big Blue and its partners in building the "Summit" supercomputer at Oak Ridge National Laboratory and "Sierra" at Lawrence Livermore National Laboratory – that would be Nvidia for GPUs and Mellanox Technologies for InfiniBand interconnect – are all about publicly focusing on the present, since these two machines are at the top of the flops charts now. We know they are actually working hard to win the next deal for the exascale successors to these two machines, but when we had a chat at the SC18 supercomputer conference with Dave Turek, vice president of technical computing and OpenPower, we didn't even bother to bring CORAL2 up. There were other interesting things to discuss. But as an aside: We did talk to Turek about CORAL2 back in June at ISC18, just after the bids for the systems had been turned in to the Department of Energy, and he couldn't say much then except that IBM should get credit for delivering Summit and Sierra more or less as planned and that this should mean a lot when it comes to the CORAL2 bids. But maybe it wouldn't because with each generation of machines, the major labs have to do an architecture survey and take into account any new developments – or lack thereof – that could offer better performance, wider application support, lower prices, or any combination of the above. In a sense, it is always back to square one on these big systems deals, which is good for driving innovation but perhaps something to make the major suppliers a bit testy until they win the deals. It seems inconceivable that the combination of the IBM Power10 chip and a future Nvidia GPU and possibly 400 Gb/sec NDR or 800 Gb/sec XDR InfiniBand won't win the CORAL2 bids, but with Cray back in the game with its own Slingshot interconnect, there is a chance that it could win at least one of the three CORAL2 machines.

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called Hardware Conditioned Policies where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training. For robots with lower zero-shot success rate, we also demonstrate that fine-tuning the policy network is significantly more sample-efficient than training a model from scratch. In tasks where knowing the agent dynamics is important for success, we learn an embedding for robot hardware and show that policies conditioned on the encoding of hardware tend to generalize and transfer well. Videos of experiments are available at: https://sites.google.com/view/robot-transfer-hcp.

Robust multi-vehicle path-planning is important for ensuring the safety of multi-vehicle systems in applications like transportation, search and rescue, and robotic exploration. Chance-constrained methods like Iterative Risk Allocation (IRA)(Ono and Williams 2008) have been developed for situations where environmental disturbances are unbounded. However, chance-constrained methods for the multi-vehicle case generally use centralized strategies where the vehicle set is planned with couplings between all vehicle pairs. This approach is intractable as fleet size increases because computation time is exponential with respect to the number of vehicles being planned over due to a polynomial increase in coupling constraints between vehicle pairs. We present a faster approach for chance-constrained multi-vehicle path-planning that relies upon a decentralized path-planning method called Risk-A ware Decentralized Model Predictive Control (RADMPC) to rapidly approximate a centralized IRA approach. The RADMPC approximation is evaluated for vehicle interactions to determine the vehicle sets that should be planned in a coupled manner. Applying IRA to the smaller vehicle sets determined from the RADMPC approximation rapidly plans safe paths for the entire fleet. A Monte Carlo simulation analysis demonstrates the correctness of our approach and a significant improvement in computation time compared to a centralized IRA approach.

One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision. Traditionally, this is accomplished by visually picking the salt/sediment boundaries, which requires a great amount of manual work and may introduce systematic bias. With recent progress of deep learning algorithm and growing computational power, a great deal of efforts have been made to replace human effort with machine power in salt body interpretation. Currently, the method of Convolutional neural networks (CNN) is revolutionizing the computer vision field and has been a hot topic in the image analysis. In this paper, the benefits of CNN-based classification are demonstrated by using a state-of-art network structure U-Net, along with the residual learning framework ResNet, to delineate salt body with high precision. Network adjustments, including the Exponential Linear Units (ELU) activation function, the Lov\'{a}sz-Softmax loss function, and stratified $K$-fold cross-validation, have been deployed to further improve the prediction accuracy. The preliminary result using SEG Advanced Modeling (SEAM) data shows good agreement between the predicted salt body and manually interpreted salt body, especially in areas with weak reflections. This indicates the great potential of applying CNN for salt-related interpretations.

This post was done in partnership with Wirecutter. When readers choose to buy Wirecutter's independently chosen editorial picks, Wirecutter and Engadget may earn affiliate commissions. Read Wirecutter's continuously updated list of Black Friday deals here. This drops the Series 3 38mm, and the 42mm ($230) to the best prices we've seen to date, almost $60 below recent sales. The Apple Watch Series 3 is the budget pick in our guide to Apple Watches. Nick Guy and Dan Frakes write, "It was introduced in 2017, but it offers most of the features and experience of the Series 4 at a significantly lower price. The Series 3 models have smaller screens--the biggest obvious difference--aren't as speedy, don't do automatic workout detection, and won't support the Series 4's ECG feature or fall detection. Even so, the Series 3 is still fast, designed with the same GPS features and swim-friendly waterproofing, and equipped with a bright screen that's easy to see outside."

Most conservation initiatives require changes in human behavior. For example, the establishment of a protected area will typically require some people to change their land-use or fishing practices. Yet conventional attempts to encourage proenvironmental behavior through awareness campaigns, financial incentives, and regulation can prove ineffective (1, 2). Insights into inducing behavior change from the social and behavioral sciences are therefore of critical importance for conservation scientists and practitioners (2–4). Conservation initiatives have begun to leverage a wide range of such behavioral insights (5) particularly regarding cognitive biases and social influence (see the figure). However, their application in the diverse socioeconomic and cultural contexts in which many conservation programs operate raises important ethical and implementation-related challenges.

Though insect-sized flying robots have been around for a while, none had been able to take untethered fight until now. Engineers at the University of Washington have revealed the RoboFly had taken its first untethered flaps, earlier this year, marking the first time a wireless flying robotic insect has flown. Now the man behind the project has revealed he hopes to have fully autonomous swarms roaming the skies within five years. RoboFly is only slightly heavier than a toothpick and is powered by an onboard circuit that converts the laser energy into enough electricity to operate its wings. Previously, the electronics the insects carried to power and control their wings were too heavy for the robots to fly with, meaning they had to remain connected to a wire.

In real-world applications such as emotion recognition from recorded brain activity, data are captured from electrodes over time. These signals constitute a multidimensional time series. In this paper, Echo State Network (ESN), a recurrent neural network with a great success in time series prediction and classification, is optimized with different neural plasticity rules for classification of emotions based on electroencephalogram (EEG) time series. Actually, the neural plasticity rules are a kind of unsupervised learning adapted for the reservoir, i.e. the hidden layer of ESN. More specifically, an investigation of Oja's rule, BCM rule and gaussian intrinsic plasticity rule was carried out in the context of EEG-based emotion recognition. The study, also, includes a comparison of the offline and online training of the ESN. When testing on the well-known affective benchmark "DEAP dataset" which contains EEG signals from 32 subjects, we find that pretraining ESN with gaussian intrinsic plasticity enhanced the classification accuracy and outperformed the results achieved with an ESN pretrained with synaptic plasticity. Four classification problems were conducted in which the system complexity is increased and the discrimination is more challenging, i.e. inter-subject emotion discrimination. Our proposed method achieves higher performance over the state of the art methods.