I write about Machine Learning • Practical tips and epic stories about my experience in the field.

We study how to use Deep Variational Autoencoders for a fast simulation of jets of particles at the LHC. We represent jets as a list of constituents, characterized by their momenta. Starting from a simulation of the jet before detector effects, we train a Deep Variational Autoencoder to return the corresponding list of constituents after detection. Doing so, we bypass both the time-consuming detector simulation and the collision reconstruction steps of a traditional processing chain, speeding up significantly the events generation workflow. Through model optimization and hyperparameter tuning, we achieve state-of-the-art precision on the jet four-momentum, while providing an accurate description of the constituents momenta, and an inference time comparable to that of a rule-based fast simulation.

Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a model from scratch with remaining training data or refining the model by reverting the model optimization on the marked data points. Unfortunately, aside from their computational inefficiency, those approaches inevitably hurt the resulting model's generalization ability since they remove not only unique characteristics but also discard shared (and possibly contributive) information. To address the performance degradation problem, this paper presents a novel approach called Performance Unchanged Model Augmentation~(PUMA). The proposed PUMA framework explicitly models the influence of each training data point on the model's generalization ability with respect to various performance criteria. It then complements the negative impact of removing marked data by reweighting the remaining data optimally. To demonstrate the effectiveness of the PUMA framework, we compared it with multiple state-of-the-art data removal techniques in the experiments, where we show the PUMA can effectively and efficiently remove the unique characteristics of marked training data without retraining the model that can 1) fool a membership attack, and 2) resist performance degradation. In addition, as PUMA estimates the data importance during its operation, we show it could serve to debug mislabelled data points more efficiently than existing approaches.

Hydropower has been stirring up controversies since the early 2000s. Despite being promoted as a solution to mitigate climate change, the hydropower bubble burst when researchers discovered in 2005 that hydropower dams are responsible for huge amounts of greenhouse gas emissions. Hydropower dams' walls restrict the flow of rivers and turn them into pools of stagnant water. Reservoir surfaces and turbines then release methane into the atmosphere. Methane makes up approximately 80 percent of the greenhouse gases emitted from hydropower dams, peaking in the first decade of the dams lifecycle.

Listed below are the key technology trends impacting the smart grid in power theme, as identified by GlobalData. By clicking the Download Free Report button, you accept the terms and conditions and acknowledge that your data will be used as described in the GlobalData Privacy Policy By downloading this Report, you acknowledge that we may share your information with our white paper partners/sponsors who may contact you directly with information on their products and services. Visit our privacy policy for more information about our services, how we may use, process and share your personal data, including information on your rights in respect of your personal data and how you can unsubscribe from future marketing communications. Our services are intended for corporate subscribers and you warrant that the email address submitted is your corporate email address. AI has an important role to play in understanding demand, and generating predictions from non-dispatchable resources such as wind and solar and from wholesale prices.

When the pandemic forced millions of people into working and collaborating remotely, it not only caused an explosion in the use and development of new technologies for productive and effective collaboration, it also made many of us more aware than ever of how technologies can enhance our thinking and creativity. At Nesta's Centre for Collective Intelligence Design, our work rests upon the premise that human intelligence combined with machine intelligence is more powerful than either in isolation. When these are successfully combined, it is known as collective intelligence. Our Grants Programme awarded funding to 15 different teams around the world that designed experiments to explore and test this idea in new ways to help tackle pressing social and environmental challenges. Each experiment fell under one of four themes: exploring artificial intelligence (AI)-crowd interaction; making better collective decisions; understanding the dynamics of collective behaviour; and gathering better data.

A new research project has found that the discretionary decisions made by human bank managers can be replicated by machine learning systems to an accuracy of more than 95%. Using the same data available to bank managers in a privileged dataset, the best-performing algorithm in the test was a Random Forest implementation – a fairly simple approach that's twenty years old, but which still outperformed a neural network when attempting to mimic the behavior of human bank managers formulating final decisions about loans. The Random Forest algorithm, one of four put through their paces for the project, achieves high human-equivalent scoring vs. performance of bank managers, despite the relative simplicity of the algorithm. The researchers, who had access to a proprietary dataset of 37,449 loan ratings across 4,414 unique customers at'a large commercial bank', suggest at various points in the preprint paper that the automated data analysis that managers are given to make their decision has now become so accurate that bank managers rarely deviate from it, potentially signifying that bank managers' part in the loan approval process chiefly consists of retaining someone to fire in the event of a loan default. 'From a practical perspective it is worth noting that our results may indicate that the bank could process loans faster and cheaper in the absence of human loan managers with very comparable results.

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions within an input video are challenging but necessary tasks for applications that require real-time human-machine interaction. By reviewing a large body of recent related work in the literature, we thoroughly analyse, explain and compare action segmentation methods and provide details on the feature extraction and learning strategies that are used on most state-of-the-art methods. We cover the impact of the performance of object detection and tracking techniques on human action segmentation methodologies. We investigate the application of such models to real-world scenarios and discuss several limitations and key research directions towards improving interpretability, generalisation, optimisation and deployment.

The graph represents a network of 1,543 Twitter users whose tweets in the requested range contained "#selfdrivingcars", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Wednesday, 23 February 2022 at 13:47 UTC. The requested start date was Wednesday, 23 February 2022 at 01:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 13-day, 5-hour, 31-minute period from Wednesday, 09 February 2022 at 14:35 UTC to Tuesday, 22 February 2022 at 20:06 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.

We investigate the performance on phoneme categorization and phoneme and word segmentation of several self-supervised learning (SSL) methods based on Contrastive Predictive Coding (CPC). Our experiments show that with the existing algorithms there is a trade off between categorization and segmentation performance. We investigate the source of this conflict and conclude that the use of context building networks, albeit necessary for superior performance on categorization tasks, harms segmentation performance by causing a temporal shift on the learned representations. Aiming to bridge this gap, we take inspiration from the leading approach on segmentation, which simultaneously models the speech signal at the frame and phoneme level, and incorporate multi-level modelling into Aligned CPC (ACPC), a variation of CPC which exhibits the best performance on categorization tasks. Our multi-level ACPC (mACPC) improves in all categorization metrics and achieves state-of-the-art performance in word segmentation.