In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study of the topic of ensemble learning for 3D point clouds. First, an ensemble of multiple model instances trained on the same part of the $\textit{ModelNet40}$ dataset was tested for seven deep learning, point cloud-based classification algorithms: $\textit{PointNet}$, $\textit{PointNet++}$, $\textit{SO-Net}$, $\textit{KCNet}$, $\textit{DeepSets}$, $\textit{DGCNN}$, and $\textit{PointCNN}$. Second, the ensemble of different architectures was tested. Results of our experiments show that the tested ensemble learning methods improve over state-of-the-art on the $\textit{ModelNet40}$ dataset, from $92.65\%$ to $93.64\%$ for the ensemble of single architecture instances, $94.03\%$ for two different architectures, and $94.15\%$ for five different architectures. We show that the ensemble of two models with different architectures can be as effective as the ensemble of 10 models with the same architecture. Third, a study on classic bagging i.e. with different subsets used for training multiple model instances) was tested and sources of ensemble accuracy growth were investigated for best-performing architecture, i.e. $\textit{SO-Net}$. We also investigate the ensemble learning of $\textit{Frustum PointNet}$ approach in the task of 3D object detection, increasing the average precision of 3D box detection on the $\textit{KITTI}$ dataset from $63.1\%$ to $66.5\%$ using only three model instances. We measure the inference time of all 3D classification architectures on a $\textit{Nvidia Jetson TX2}$, a common embedded computer for mobile robots, to allude to the use of these models in real-life applications.

This paper presents a taxonomy of explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability, and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it will need to evaluate all other issues regarding explainability.

Traffic congestion is a growing problem that continues to plague urban areas with negative outcomes to both the traveling public and society as a whole. These negative outcomes will only grow over time as more people flock to urban areas. In 2014, traffic congestion costs Americans over $160 billion in lost productivity and wasted over 3.1 billion gallons of fuel [Economist 2014]. Traffic congestion was also attributed to over 56 billion pounds of harmful CO2 emissions in 2011 [Schrank et al. 2015]. In the European Union, the cost of traffic congestion was equivalent to 1% of the entire GDP [Schrank et al. 2012]. Mitigating congestion would have significant economic, environmental and societal benefits. Signalized intersections are one of the most prevalent bottleneck types in urban environments, and thus traffic signal control plays a vital role in urban traffic management.

In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far obtains F1 score of 75.842% and EM score of 72.24% on the test PCE leaderboad.

Hundreds of human reviewers across the globe, from Romania to Venezuela, listen to audio clips recorded from Amazon Echo speakers, usually without owners' knowledge, Bloomberg reported last week. We knew Alexa was listening; now we know someone else is, too. This global review team fine-tunes the Amazon Echo's software by listening to clips of users asking Alexa questions or issuing commands, and then verifying whether Alexa responded appropriately. The team also annotates specific words the device struggles with when it's addressed in different accents. According to Amazon, users can opt out of the service, but they seem to be enrolled automatically.

Fully autonomous vehicles may still technically be on the horizon, but according to CEO Elon Musk, Tesla's dominance of the market is already'game, set, and match.' In an interview with MIT researcher, Lex Fridman, Musk claims that the company should achieve its quest for fully autonomous vehicles in as little as six months, and at the most, in one year. As reported by Ars Technica, Musk said that the vehicles could come to fruition'maybe even toward the end of this year,' adding, 'I'd be shocked if it's not next year at the latest.' Tesla CEO Elon Musk says fully autonomous vehicles are around the corner, but agggresive estimates have drawn criticism from industry experts. While Musk's claims that Tesla will be delivering the world's first fully autonomous vehicles on an expedited timeline, the forecast has raised the eyebrows of industry skeptics who say the company's overblown projections constitute false advertising at best.

SpaceX says it lost the Falcon Heavy's center core after'rough sea conditions' caused it to topple over as it was being transported back to the Florida coast. Elon Musk's rocket company managed to make history on Thursday when it landed three boosters back on Earth for the first time, following the Falcon Heavy megarocket's successful second launch into space. But as ocean swells continued to rise, wave heights caused the center core to fall off of the company's drone ship, dubbed'Of Course I Still Love You,' which is stationed in the Atlantic Ocean, according to the Verge. SpaceX says it lost the Falcon Heavy's center core (pictured) after'rough sea conditions' caused it to topple over as it was being transported back to the Florida coast'Over the weekend, due to rough sea conditions, SpaceX's recovery team was unable to secure the center booster for its return trip to Port Canaveral,' SpaceX said in a statement. 'As conditions worsened with eight to ten foot swells, the booster began to shift and ultimately was unable to remain upright.

Many are concerned about the amount of time we – and our children – spend on devices. Soon to be a father, Prince Harry recently suggested "social media is more addictive than drugs and alcohol, yet it's more dangerous because it's normalised and there are no restrictions to it". But worries are not just limited to personal use. Many schools and workplaces are increasingly delivering content digitally, and even using game-playing elements like point scoring and competition with others in non-game contexts to drive better performance. This "always on" lifestyle means many can't just "switch off".

Sony has revealed the first details of the PS5, giving a wide-ranging look at what's inside the brand new console. The console will include a whole host of new hardware including CPUs and GPUs that can power technologies never before seen outside of the highest end computers, PlayStation claimed. But perhaps it's most significant new feature, which it says will be "a true game changer", is a new hard drive. The much faster solid state drive will allow the console to work far more quickly than existing hardware. An operation that once took 15 seconds will now take less than one, according to its architect Mark Cerny, who revealed the plans in an interview with Wired.

Logitech's popular Harmony universal remotes have long been the go-to solution for tech-savvy nerds who want to replace the bounty of ugly rectangles littering their coffee tables with a single, all-powerful option. But universal remotes are still pretty complex on their own, with dozens of buttons and, in some cases, LCD screens. You're basically swapping several remotes for something that looks like it belongs in one of NASA's Mission Control Centers. Now, there's something simpler: the Harmony Express, a compact universal remote that replaces a slew of buttons with Amazon Alexa voice controls. The $250 Express isn't meant to replace the Harmony Elite, which Logitech released back in 2015 and is still one of the best high-end universal remotes around.