The 40th International Conference on Machine Learning (ICML) took place Honolulu, Hawai'i from 23-29 July 2023. There were four invited talks as part of the programme, and in this post we summarise the presentation by Shakir Mohamed – "Machine learning with social purpose". In a talk of three interwoven parts, Shakir's aim was to encourage the amplification and acceleration of work on machine learning with social purpose. He is passionate about using machine learning to contribute to overcoming some of the global challenges that we face, and, as well as demonstrating some of his research in this space, he provided guidance on how researchers can widen their horizons and consider the social implications of their work. Modelling of weather and climate can have a big impact on society, with such models often providing the basis for decisions taken by policy makers.

The modeling of high-frequency data that qualify financial asset transactions has been an area of relevant interest among statisticians and econometricians -- above all, the analysis of time series of financial durations. Autoregressive conditional duration (ACD) models have been the main tool for modeling financial transaction data, where duration is usually defined as the time interval between two successive events. These models are usually specified in terms of a time-varying mean (or median) conditional duration. In this paper, a new extension of ACD models is proposed which is built on the basis of log-symmetric distributions reparametrized by their quantile. The proposed quantile log-symmetric conditional duration autoregressive model allows us to model different percentiles instead of the traditionally used conditional mean (or median) duration. We carry out an in-depth study of theoretical properties and practical issues, such as parameter estimation using maximum likelihood method and diagnostic analysis based on residuals. A detailed Monte Carlo simulation study is also carried out to evaluate the performance of the proposed models and estimation method in retrieving the true parameter values as well as to evaluate a form of residuals. Finally, the proposed class of models is applied to a price duration data set and then used to derive a semi-parametric intraday value-at-risk (IVaR) model.

Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data. To this end, we develop a comprehensive and robust framework NBIAS that consists of four main layers: data, corpus construction, model development and an evaluation layer. The dataset is constructed by collecting diverse data from various domains, including social media, healthcare, and job hiring portals. As such, we applied a transformer-based token classification model that is able to identify bias words/ phrases through a unique named entity BIAS. In the evaluation procedure, we incorporate a blend of quantitative and qualitative measures to gauge the effectiveness of our models. We achieve accuracy improvements ranging from 1% to 8% compared to baselines. We are also able to generate a robust understanding of the model functioning. The proposed approach is applicable to a variety of biases and contributes to the fair and ethical use of textual data.

The real-time crash likelihood prediction model is an essential component of the proactive traffic safety management system. Over the years, numerous studies have attempted to construct a crash likelihood prediction model in order to enhance traffic safety, but mostly on freeways. In the majority of the existing studies, researchers have primarily employed a deep learning-based framework to identify crash potential. Lately, Transformer has emerged as a potential deep neural network that fundamentally operates through attention-based mechanisms. Transformer has several functional benefits over extant deep learning models such as LSTM, CNN, etc. Firstly, Transformer can readily handle long-term dependencies in a data sequence. Secondly, Transformers can parallelly process all elements in a data sequence during training. Finally, a Transformer does not have the vanishing gradient issue. Realizing the immense possibility of Transformers, this paper proposes inTersection-Transformer (inTformer), a time-embedded attention-based Transformer model that can effectively predict intersection crash likelihood in real-time. The proposed model was evaluated using connected vehicle data extracted from Signal Analytics Platform. Acknowledging the complex traffic operation mechanism at intersection, this study developed zone-specific models by dividing the intersection region into two distinct zones: within-intersection and approach zone. The best inTformer models in 'within-intersection,' and 'approach' zone achieved a sensitivity of 73%, and 70%, respectively. The zone-level models were also compared to earlier studies on crash likelihood prediction at intersections and with several established deep learning models trained on the same connected vehicle dataset.

Farmers must continuously improve their livestock production systems to remain competitive in the growing dairy market. Precision livestock farming technologies provide individualized monitoring of animals on commercial farms, optimizing livestock production. Continuous acoustic monitoring is a widely accepted sensing technique used to estimate the daily rumination and grazing time budget of free-ranging cattle. However, typical environmental and natural noises on pastures noticeably affect the performance limiting the practical application of current acoustic methods. In this study, we present the operating principle and generalization capability of an acoustic method called Noise-Robust Foraging Activity Recognizer (NRFAR). The proposed method determines foraging activity bouts by analyzing fixed-length segments of identified jaw movement events produced during grazing and rumination. The additive noise robustness of the NRFAR was evaluated for several signal-to-noise ratios using stationary Gaussian white noise and four different nonstationary natural noise sources. In noiseless conditions, NRFAR reached an average balanced accuracy of 86.4%, outperforming two previous acoustic methods by more than 7.5%. Furthermore, NRFAR performed better than previous acoustic methods in 77 of 80 evaluated noisy scenarios (53 cases with p<0.05). NRFAR has been shown to be effective in harsh free-ranging environments and could be used as a reliable solution to improve pasture management and monitor the health and welfare of dairy cows. The instrumentation and computational algorithms presented in this publication are protected by a pending patent application: AR P20220100910. Web demo available at: https://sinc.unl.edu.ar/web-demo/nrfar

Due to advancements in information technology and the rapid rise of the Internet, the data revolution of the past several decades has caused businesses to create more data than they can utilize or understand (see Erevelles, S.; Fukawa, N.; Swayne, L., 2016; Seng, J.L.; Chen, T., 2010). The expansion in the volume of data, the variety of data kinds, and the scope of analysis has necessitated technological advancements beyond storage, transport, and processing (see Seng, J.L.; Chen, T., 2010) The data must be translated into information and knowledge in order to transfer knowledge into decision-making tools for enterprises. This data is used in marketing research to identify intriguing links between market segmentation in industrial, tourist, and other markets, customer lifetime value, loyalty and client segment, direct market, marketing campaign, and other applications (Tkáˇc, M.; Verner, R., 2016). With the application of Machine Learning (ML) methods (see Bahari, T.F.; Elayidom, M.S., 2015; Jessen, H.C.; Paliouras, G., 2001), it is currently anticipated that enormous volumes of stored data may be explored, and usable information extracted. ML are strategies that equip computers with the capacity to comprehend, using data and experiences similar to the human brain (Çelik, Ö., 2018).

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown promising capabilities in planning and navigating open-world scenarios. This paper introduces a novel application of pre-trained LLMs as agents within cybersecurity network environments, focusing on their utility for sequential decision-making processes. We present an approach wherein pre-trained LLMs are leveraged as attacking agents in two reinforcement learning environments. Our proposed agents demonstrate similar or better performance against state-of-the-art agents trained for thousands of episodes in most scenarios and configurations. In addition, the best LLM agents perform similarly to human testers of the environment without any additional training process. This design highlights the potential of LLMs to efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.

The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various segmentation tasks. However, the current pipeline requires manual prompts during the inference stage, which is still resource intensive for biomedical image segmentation. In this paper, instead of using prompts during the inference stage, we introduce a pipeline that utilizes the SAM, called all-in-SAM, through the entire AI development workflow (from annotation generation to model finetuning) without requiring manual prompts during the inference stage. Specifically, SAM is first employed to generate pixel-level annotations from weak prompts (e.g., points, bounding box). Then, the pixel-level annotations are used to finetune the SAM segmentation model rather than training from scratch. Our experimental results reveal two key findings: 1) the proposed pipeline surpasses the state-of-the-art (SOTA) methods in a nuclei segmentation task on the public Monuseg dataset, and 2) the utilization of weak and few annotations for SAM finetuning achieves competitive performance compared to using strong pixel-wise annotated data.

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving. However, manually creating or re-creating real-world-like environments is difficult, expensive, and not scalable. Recent generative model techniques have shown promising progress to address such challenges by learning 3D assets using only plentiful 2D images -- but still suffer limitations as they leverage either human-curated image datasets or renderings from manually-created synthetic 3D environments. In this paper, we introduce GINA-3D, a generative model that uses real-world driving data from camera and LiDAR sensors to create realistic 3D implicit neural assets of diverse vehicles and pedestrians. Compared to the existing image datasets, the real-world driving setting poses new challenges due to occlusions, lighting-variations and long-tail distributions. GINA-3D tackles these challenges by decoupling representation learning and generative modeling into two stages with a learned tri-plane latent structure, inspired by recent advances in generative modeling of images. To evaluate our approach, we construct a large-scale object-centric dataset containing over 1.2M images of vehicles and pedestrians from the Waymo Open Dataset, and a new set of 80K images of long-tail instances such as construction equipment, garbage trucks, and cable cars. We compare our model with existing approaches and demonstrate that it achieves state-of-the-art performance in quality and diversity for both generated images and geometries.

The growing number of exoplanet discoveries and advances in machine learning techniques have opened new avenues for exploring and understanding the characteristics of worlds beyond our Solar System. In this study, we employ efficient machine learning approaches to analyze a dataset comprising 762 confirmed exoplanets and eight Solar System planets, aiming to characterize their fundamental quantities. By applying different unsupervised clustering algorithms, we classify the data into two main classes: 'small' and 'giant' planets, with cut-off values at $R_{p}=8.13R_{\oplus}$ and $M_{p}=52.48M_{\oplus}$. This classification reveals an intriguing distinction: giant planets have lower densities, suggesting higher H-He mass fractions, while small planets are denser, composed mainly of heavier elements. We apply various regression models to uncover correlations between physical parameters and their predictive power for exoplanet radius. Our analysis highlights that planetary mass, orbital period, and stellar mass play crucial roles in predicting exoplanet radius. Among the models evaluated, the Support Vector Regression consistently outperforms others, demonstrating its promise for obtaining accurate planetary radius estimates. Furthermore, we derive parametric equations using the M5P and Markov Chain Monte Carlo methods. Notably, our study reveals a noteworthy result: small planets exhibit a positive linear mass-radius relation, aligning with previous findings. Conversely, for giant planets, we observe a strong correlation between planetary radius and the mass of their host stars, which might provide intriguing insights into the relationship between giant planet formation and stellar characteristics.