Disruptions in energy imports, backlash in social acceptance, and novel technologies failing to develop are unexpected events that are often overlooked in energy planning, despite their ability to jeopardize the energy transition. We propose a method to explore unexpected events and assess their impact on the transition pathway of a large-scale whole-energy system. First, we evaluate unexpected events assuming "perfect foresight", where decision-makers can anticipate such events in advance. This allows us to identify dealbreakers, i.e., conditions that make the transition infeasible. Then, we assess the events under "limited foresight" to evaluate the robustness of early-stage decisions against unforeseen unexpected events and the costs associated with managing them. A case study for Belgium demonstrates that a lack of electrofuel imports in 2050 is the main dealbreaker, while accelerating the deployment of renewables is the most robust policy. Our transferable method can help policymakers identify key dealbreakers and devise robust energy transition policies.

The commonsense reasoning capabilities of vision-language models (VLMs), especially in abductive reasoning and defeasible reasoning, remain poorly understood. Most benchmarks focus on typical visual scenarios, making it difficult to discern whether model performance stems from keen perception and reasoning skills, or reliance on pure statistical recall. We argue that by focusing on atypical events in videos, clearer insights can be gained on the core capabilities of VLMs. Explaining and understanding such out-of-distribution events requires models to extend beyond basic pattern recognition and regurgitation of their prior knowledge. To this end, we introduce BlackSwanSuite, a benchmark for evaluating VLMs' ability to reason about unexpected events through abductive and defeasible tasks. Our tasks artificially limit the amount of visual information provided to models while questioning them about hidden unexpected events, or provide new visual information that could change an existing hypothesis about the event. We curate a comprehensive benchmark suite comprising over 3,800 MCQ, 4,900 generative and 6,700 yes/no tasks, spanning 1,655 videos. After extensively evaluating various state-of-the-art VLMs, including GPT-4o and Gemini 1.5 Pro, as well as open-source VLMs such as LLaVA-Video, we find significant performance gaps of up to 32% from humans on these tasks. Our findings reveal key limitations in current VLMs, emphasizing the need for enhanced model architectures and training strategies.

The ability of an agent to change its objectives in response to unexpected events is desirable in dynamic environments. In order to provide this capability to hierarchical task network (HTN) planning, we propose an extension of the paradigm called task modifiers, which are functions that receive a task list and a state and produce a new task list. We focus on a particular type of problems in which planning and execution are interleaved and the ability to handle exogenous events is crucial. To determine the efficacy of this approach, we evaluate the performance of our task modifier implementation in two environments, one of which is a simulation that differs substantially from traditional HTN domains.

But according to IEEE Spectrum the inability of a typical deep learning program to perform well on more than one task, for example, severely limits the application of the technology to specific tasks in rigidly controlled environments. More seriously deep learning is untrustworthy because it is not explainable -- and unsuitable for some applications because it can experience catastrophic forgetting. If the algorithm works, it may be impossible to fully understand why. And while the tool is slowly learning a new database, an arbitrary part of its learned memories can suddenly collapse. Therefore, it might be risky to use deep learning on any life-or-death application, such as a medical one.

The answers people give when asked to 'think of the unexpected' for everyday event scenarios appear to be more expected than unexpected. There are expected unexpected outcomes that closely adhere to the given information in a scenario, based on familiar disruptions and common plan-failures. There are also unexpected unexpected outcomes that are more inventive, that depart from given information, adding new concepts/actions. However, people seem to tend to conceive of the unexpected as the former more than the latter. Study 1 tests these proposals by analysing the object-concepts people mention in their reports of the unexpected and the agreement between their answers. Study 2 shows that object-choices are weakly influenced by recency, the order of sentences in the scenario. The implications of these results for ideas in philosophy, psychology and computing is discussed

Quant funds are expected to account for US$1 trillion in assets this year. But when algorithms are managing this money, who manages the algorithms? Computer-powered, data-driven strategies have continued their spectacular march towards dominating the hedge fund industry. According to research by HFR, the amount of money being managed by quant hedge funds rose to more than $940 billion by the end of October 2017 and is on course to pass the $1 trillion at some point this year. This is an enormous amount of money being managed by machines.

Security cameras are great, but only when they're actually pointed at whatever is going on. Alarm has developed a machine learning algorithm, called the Insights Engine, that continually monitors sensors placed around your property to learn how things are normally run and to quickly identify unexpected events -- say, a break-in or a water leak -- when they occur. If the system does spot something out of the ordinary, it will deploy a swarm of autonomous UAVs built on Qualcomm's Snapdragon Flight drone platform to investigate. These little fliers will swarm over the event site and provide live video feeds to your phone. You can also opt in to share that video data with either Alarm.com's

As it wraps up its annual user conference here this week, San Francisco-based Splunk has one main message for the market. It's going big -- or, given that this is football season -- long with machine learning. In other words, it has expanded in a significant way the early version of machine learning in its platform to deliver new services and capabilities. It has added machine learning to the core of its platform with a machine learning toolkit that can be installed as a free app on top of the Splunk Enterprise platform, Manish Sainani, principal product manager of Machine Learning at Splunk told CMSWire. This toolkit provides 300 algorithms for machine learning, 27 of which are pre-packaged out of the box, spanning all of the major categories, he said.

Unexpected stimuli are a challenge to any machine learning algorithm. Here we identify distinct types of unexpected events, focusing on 'incongruent events' - when 'general level' and 'specific level' classifiers give conflicting predictions. We define a formal framework for the representation and processing of incongruent events: starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies. For each event, we compute its probability in different ways, based on adjacent levels (according to the partial order) in the label hierarchy . An incongruent event is an event where the probability computed based on some more specific level (in accordance with the partial order) is much smaller than the probability computed based on some more general level, leading to conflicting predictions. We derive algorithms to detect incongruent events from different types of hierarchies, corresponding to class membership or part membership. Respectively, we show promising results with real data on two specific problems: Out Of Vocabulary words in speech recognition, and the identification of a new sub-class (e.g., the face of a new individual) in audio-visual facial object recognition.

In real-world domains (e.g., a mobile robot environment), things do not always proceed as planned, so it is important to develop better execution-monitoring techniques and replanning capabilities. This paper describes these capabilities in the SIPE (System for Interactive Planning and Execution Monitoring) planning system. The motivation behind SIPE is to place enough limitations on the representation so that planning can be done efficiently, while retaining sufficient power to still be useful. This work assumes that new information given to the execution monitor is in the form of predicates, thus avoiding the difficult problem of how to generate these predicates from information provided by sensors. The replanning module presented here takes advantage of the rich structure of SIPE plans and is intimately connected with the planner, which can be called as a subroutine.