The Aiper Scuba X1 looks--and is priced--like a high-end robotic pool cleaner, but it's a weak performer and it's a bear to clean after a session in the pool. Aiper makes some excellent robotic pool cleanrs--such as its stellar workhorse, the Seagull Pro--but it also has a few duds in its arsenal, including the Seagull Plus and the Scuba S1. With its latest robot, the Scuba X1, Aiper looks to bring some higher-end features (including smart connectivity) to the lineup. With a street price of 1,200, it's one of Aiper's most expensive models–and it's got the gold trim to prove it. The Aiper Scuba X1 doesn't change the basic design that most of Aiper's full-size robots have followed for years: Compare its design to the aforementioned Seagull Pro, Seagull Plus, and Scuba S1.

In the last few years, due to the broad applicability of deep learning to downstream tasks and end-to-end training capabilities, increasingly more concerns about potential biases to specific, non-representative patterns have been raised. Many works focusing on unsupervised debiasing usually leverage the tendency of deep models to learn ``easier'' samples, for example by clustering the latent space to obtain bias pseudo-labels. However, the interpretation of such pseudo-labels is not trivial, especially for a non-expert end user, as it does not provide semantic information about the bias features. To address this issue, we introduce ``Say My Name'' (SaMyNa), the first tool to identify biases within deep models semantically. Unlike existing methods, our approach focuses on biases learned by the model. Our text-based pipeline enhances explainability and supports debiasing efforts: applicable during either training or post-hoc validation, our method can disentangle task-related information and proposes itself as a tool to analyze biases. Evaluation on traditional benchmarks demonstrates its effectiveness in detecting biases and even disclaiming them, showcasing its broad applicability for model diagnosis.

Unmanned aerial vehicles assist in maritime search and rescue missions by flying over large search areas to autonomously search for objects or people. Reliably detecting objects of interest requires fast models to employ on embedded hardware. Moreover, with increasing distance to the ground station only part of the video data can be transmitted. In this work, we consider the problem of finding meaningful region of interest proposals in a video stream on an embedded GPU. Current object or anomaly detectors are not suitable due to their slow speed, especially on limited hardware and for large image resolutions. Lastly, objects of interest, such as pieces of wreckage, are often not known a priori. Therefore, we propose an end-to-end future frame prediction model running in real-time on embedded GPUs to generate region proposals. We analyze its performance on large-scale maritime data sets and demonstrate its benefits over traditional and modern methods.

Five-year-old pool cleaning company Aiper is launching the Seagull Pro, which the company says is the world's first quad-motor pool-cleaning robot. The flagship vacuum is a CES 2023 Innovation Award Honoree. The Seagull Pro's quad-motor system moves the robot around your pool by sucking and quickly exhausting water. Aiper says it can "suck in dirt, sand, leaves, hairs and other particles on the pool's floor more efficiently than other models." It can clean in- or above-ground pools (up to 3,200 sq. Aiper says the device's WavePath Navigation follows "a unique wave shape" while cleaning to increase its coverage compared to vacuums that wander randomly.

Despite broad interest in applying deep learning techniques to scientific discovery, learning interpretable formulas that accurately describe scientific data is very challenging because of the vast landscape of possible functions and the "black box" nature of deep neural networks. The key to success is to effectively integrate existing knowledge or hypotheses about the underlying structure of the data into the architecture of deep learning models to guide machine learning. Currently, such integration is commonly done through customization of the loss functions. Here we propose an alternative approach to integrate existing knowledge or hypotheses of data structure by constructing custom activation functions that reflect this structure. Specifically, we study a common case when the multivariate target function $f$ to be learned from the data is partially exchangeable, \emph{i.e.} $f(u,v,w)=f(v,u,w)$ for $u,v\in \mathbb{R}^d$. For instance, these conditions are satisfied for the classification of images that is invariant under left-right flipping. Through theoretical proof and experimental verification, we show that using an even activation function in one of the fully connected layers improves neural network performance. In our experimental 9-dimensional regression problems, replacing one of the non-symmetric activation functions with the designated "Seagull" activation function $\log(1+x^2)$ results in substantial improvement in network performance. Surprisingly, even activation functions are seldom used in neural networks. Our results suggest that customized activation functions have great potential in neural networks.

Turing proposed his test in a spirit of down-to-earth pragmatism. He saw that, when faced with the question, "Is it possible to build a machine that can think?", Turing hoped that his test would cut through a lot of fruitless semantic debate. It was an engineer's solution, rather than a philosopher's. Perhaps inevitably, Turing's proposal merely redirected the philosophical debate. Instead of quarrelling about the meaning of the verb "to think", philosophers argued about the meaning of the Turing test instead.

The Seagull is an unmanned vehicle. The torpedo is a torpedo. A robotic ship fired a torpedo into the ocean without any humans aboard. Naval battles, for so long the domain of sailors fighting each other and the elements all at once, can now be in part delegated to machines. The vessel responsible is the Seagull Unmanned Surface Vessel, made by Israel's Elbit Systems.