Recent approaches for vision-language models (VLMs) have shown remarkable success in achieving fast downstream adaptation. When applied to real-world downstream tasks, VLMs inevitably encounter both the in-distribution (ID) data and out-of-distribution (OOD) data. The OOD datasets often include both covariate shifts (e.g., known classes with changes in image styles) and semantic shifts (e.g., test-time unseen classes). This highlights the importance of improving VLMs' generalization ability to covariate-shifted OOD data, while effectively detecting open-set semantic-shifted OOD classes. In this paper, inspired by the substantial energy change observed in closed-set data when re-aligning vision-language modalities--specifically by directly reducing the maximum cosine similarity to a low value--we introduce a novel OOD score, named Energy.

A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge. In this paper we show that energy-based models can exhibit this ability by directly combining probability distributions. Samples from the combined distribution correspond to compositions of concepts. For example, given a distribution for smiling faces, and another for male faces, we can combine them to generate smiling male faces. This allows us to generate natural images that simultaneously satisfy conjunctions, disjunctions, and negations of concepts. We evaluate compositional generation abilities of our model on the CelebA dataset of natural faces and synthetic 3D scene images. We also demonstrate other unique advantages of our model, such as the ability to continually learn and incorporate new concepts, or infer compositions of concept properties underlying an image.

Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited relevance to practical situations. A more general and useful problem is arbitrary conditional density estimation, which aims to model any possible conditional distribution over a set of covariates, reflecting the more realistic setting of inference based on prior knowledge. We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution $p(\mathbf{x}_u \mid \mathbf{x}_o)$ for all possible subsets of unobserved features $\mathbf{x}_u$ and observed features $\mathbf{x}_o$. ACE is designed to avoid unnecessary bias and complexity --- we specify densities with a highly expressive energy function and reduce the problem to only learning one-dimensional conditionals (from which more complex distributions can be recovered during inference). This results in an approach that is both simpler and higher-performing than prior methods. We show that ACE achieves state-of-the-art for arbitrary conditional likelihood estimation and data imputation on standard benchmarks.

ABSTRACT Natural gas (NG) is relatively a clean source of energy, particularly compared to fossil fuels, and worldwide consumption of NG has been increasing almost linearly in the last two decades. A similar trend can also be seen in Turkey, while another similarity is the high dependence on impor ts for the continuous NG supply. It is crucial to accurately forecast future NG demand (NGD) in Turkey, especially, for import contracts; in this respect, forecasts of monthly NGD for the following year are of utmost importance. In the current study, the h istorical monthly NG consumption data between 2014 and 2024 provided by SOCAR, the local residential NG distribution company for two cities in Turkey, Bursa and Kayseri, was used to determine out - of - sample monthly NGD forecasts for a period of one year and nine months using various time series models, including SARIMA and ETS models, and a novel proposed machine learning method. The proposed method, named Just - in - Time - Learning - Gaussia n Process Regression (JITL - GPR), uses a novel feature representation for t he past NG demand values; instead of using past demand values as column - wise separate features, they are placed on a two - dimensional (2 - D) grid of year - month values. For each test point, a kernel function, tailored for the NGD predictions, is used in GPR t o predict the query point. Since a model is constructed separately for each test point, the proposed method is, indeed, an example of JITL. The JITL - GPR method is easy to use and optimize, and offers a reduction in forecast errors compared to traditional t ime series methods and a state - of - the - art combinat ion model; therefore, it is a promising tool for NGD forecasting in similar settings. INTRODUCTION In the last few decades, there has been a shift in energy sources from fossil fuels to cleaner energy sources, such as wind and solar energy, mainly due to environmental concerns and related government regulations . However, these latter sources are depend ent on w eather conditions and require integration with grid technologies for continuous power generation. Natural gas (NG), typically, consists of (up to) ~95% of methane and 2 - 2.5% ethane - hexane+, with the remain der consist ing of nitrogen, CO NG p ower plants are easy to build and highly reliable, mak ing them invaluable for "clean" energy production. On the other hand, m ost countries depend on imports to maintain t heir NG supplies, and there is a delicate balance between import s and domestic demand . S toring excess import ed gas above actual demand is difficult and would result in economic losses, while import ing less than actual demand could result in a nationwide sh ortage.

We propose a reinforcement learning strategy to control wind turbine energy generation by actively changing the rotor speed, the rotor yaw angle and the blade pitch angle. A double deep Q-learning with a prioritized experience replay agent is coupled with a blade element momentum model and is trained to allow control for changing winds. The agent is trained to decide the best control (speed, yaw, pitch) for simple steady winds and is subsequently challenged with real dynamic turbulent winds, showing good performance. The double deep Q- learning is compared with a classic value iteration reinforcement learning control and both strategies outperform a classic PID control in all environments. Furthermore, the reinforcement learning approach is well suited to changing environments including turbulent/gusty winds, showing great adaptability. Finally, we compare all control strategies with real winds and compute the annual energy production. In this case, the double deep Q-learning algorithm also outperforms classic methodologies.

As efforts to mitigate the effects of climate change grow, reliable and thorough reporting of greenhouse gas emissions are essential for measuring progress towards international and domestic emissions reductions targets. New Zealand's national emissions inventories are currently reported between 15 to 27 months out-of-date. We present a machine learning approach to nowcast (dynamically estimate) national greenhouse gas emissions in New Zealand in advance of the national emissions inventory's release, with just a two month latency due to current data availability. Key findings include an estimated 0.2% decrease in national gross emissions since 2020 (as at July 2022). Our study highlights the predictive power of a dynamic view of emissions intensive activities. This methodology is a proof of concept that a machine learning approach can make sub-annual estimates of national greenhouse gas emissions by sector with a relatively low error that could be of value for policy makers.

The heat capacity of a material is a fundamental property of great practical importance. For example, in a carbon capture process, the heat required to regenerate a solid sorbent is directly related to the heat capacity of the material. However, for most materials suitable for carbon capture applications, the heat capacity is not known, and thus the standard procedure is to assume the same value for all materials. In this work, we developed a machine learning approach, trained on density functional theory simulations, to accurately predict the heat capacity of these materials, that is, zeolites, metal–organic frameworks and covalent–organic frameworks. The accuracy of our prediction is confirmed with experimental data. Finally, for a temperature swing adsorption process that captures carbon from the flue gas of a coal-fired power plant, we show that for some materials, the heat requirement is reduced by as much as a factor of two using the correct heat capacity. Heat capacity of nanoporous materials is important for processes such as carbon capture, as this can affect process design energy requirements. Here, a machine learning approach for heat capacity prediction, trained on density functional theory simulations, is presented and experimentally verified.

AUNTIE BEEB is embracing the AI revolution with two nights of programming generated by a neural network offering a juxtaposition between bleeding edge tech and vintage television. Eagle-eyed viewers will have spotted'BBC 4.1 - Artificial Intelligence TV' has been trailing for a couple of weeks, assuring viewers they can'Relax - It's going to be fine'. Alongside programming about AI itself, 'Made by Machine: When AI met The Archive' will show a range of classic clips from over 250,000 shows since 1953, selected by an AI, trained to know what BBC Four is, what it shows and what its viewers will like. The experimental programming has unearthed some'hidden gems' that haven't been seen in years, and which manual research alone would have taken hundreds of hours of research - if indeed they were found at all. The slight elephant in the room is that, given that the BBC recycled and junked many master tapes during the 1970s and 1980s, some of the suggestions may no longer exist.

Azeem Azhar is a strategist, product entrepreneur, and analyst living in London. He is the curator of the weekly newsletter Exponential View, from which the following is adapted. This is the first year I am presenting predictions for the coming year. I've received some incredibly helpful comments from readers via Twitter. This has encouraged me to stick my head above the parapet.

At a recent conference in 2017, Microsoft CEO Satya Nadella used the analogy of a corn maze to explain the difference in approach between a classical computer and a quantum computer. In trying to find a path through the maze, a classical computer would start down a path, hit an obstruction, backtrack; start again, hit another obstruction, backtrack again until it ran out of options. Although an answer can be found, this approach could be a very time-consuming. They take every path in the corn maze simultaneously." Thus, leading to an exponential reduction in the number of steps required to solve a problem.