Practical applications of machine learning often involve successive training iterations with changes to features and training examples.

Practical applications of machine learning often involve successive training iterations with changes to features and training examples.

Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows us to represent predictions as linear combinations of semantically meaningful components. Empirical evaluations demonstrate that XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.

Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems. However, these approximators introduce challenges due to the non-stationary nature of RL training. One source of the challenges in RL is that output predictions can churn, leading to uncontrolled changes after each batch update for states not included in the batch. Although such a churn phenomenon exists in each step of network training, how churn occurs and impacts RL remains under-explored. In this work, we start by characterizing churn in a view of Generalized Policy Iteration with function approximation, and we discover a chain effect of churn that leads to a cycle where the churns in value estimation and policy improvement compound and bias the learning dynamics throughout the iteration. Further, we concretize the study and focus on the learning issues caused by the chain effect in different settings, including greedy action deviation in value-based methods, trust region violation in proximal policy optimization, and dual bias of policy value in actor-critic methods. We then propose a method to reduce the chain effect across different settings, called Churn Approximated ReductIoN (CHAIN), which can be easily plugged into most existing DRL algorithms. Our experiments demonstrate the effectiveness of our method in both reducing churn and improving learning performance across online and offline, value-based and policy-based RL settings, as well as a scaling setting.

Fraudsters are using the latest AI technology to churn out masses of high-quality fake IDs in just minutes, a report has warned. Yoti, which provides facial estimation systems for British supermarkets and pubs to check users are over-18, said the forgeries were so'sophisticated' they were hard to spot. The British firm highlighted an underground website called Onlyfake that used the technology behind chatbots to create'highly convincing' AI-generated IDs for just 12. With a reported 20,000 being produced every day, an investigation found they were good enough to bypass an online trading platform's strict verification system. Security experts said supermarkets, pubs, and airports would also need to be on ' red alert' - warning many were'woefully unprepared to deal with this threat'.

Practical applications of machine learning often involve successive training iterations with changes to features and training examples. Ideally, changes in the output of any new model should only be improvements (wins) over the previous iteration, but in practice the predictions may change neutrally for many examples, resulting in extra net-zero wins and losses, referred to as unnecessary churn. These changes in the predictions are problematic for usability for some applications, and make it harder and more expensive to measure if a change is statistically significant positive. In this paper, we formulate the problem and present a stabilization operator to regularize a classifier towards a previous classifier. We use a Markov chain Monte Carlo stabilization operator to produce a model with more consistent predictions without adversely affecting accuracy. We investigate the properties of the proposal with theoretical analysis. Experiments on benchmark datasets for different classification algorithms demonstrate the method and the resulting reduction in churn.

Practical applications of machine learning often involve successive training iterations with changes to features and training examples. Ideally, changes in the output of any new model should only be improvements (wins) over the previous iteration, but in practice the predictions may change neutrally for many examples, resulting in extra net-zero wins and losses, referred to as unnecessary churn. These changes in the predictions are problematic for usability for some applications, and make it harder and more expensive to measure if a change is statistically significant positive. In this paper, we formulate the problem and present a stabilization operator to regularize a classifier towards a previous classifier. We use a Markov chain Monte Carlo stabilization operator to produce a model with more consistent predictions without adversely affecting accuracy. We investigate the properties of the proposal with theoretical analysis. Experiments on benchmark datasets for different classification algorithms demonstrate the method and the resulting reduction in churn.

The Luddites have a bad reputation. These days, the word is most commonly used as an insult--shorthand for somebody who doesn't understand new technology, is skeptical of progress, and wants to remain stuck in the ways of the past. That perception couldn't be more wrong, according to Brian Merchant. In his new book, Blood in the Machine, Merchant argues that understanding the true history of the Luddites is vital for workers today grappling with the rise of artificial intelligence (AI) and automation in the workplace. "At least in my lifetime, the Luddites have never been more relevant," Merchant, 39, tells TIME. "We are confronting a series of cases where technology is being used by tech companies and executives in different industries as a means of trying to drive down wages and worsen conditions so that the entrepreneurial class can make more money."

Customer churn describes terminating a relationship with a business or reducing customer engagement over a specific period. Two main business marketing strategies play vital roles to increase market share dollar-value: gaining new and preserving existing customers. Customer acquisition cost can be five to six times that for customer retention, hence investing in customers with churn risk is smart. Causal analysis of the churn model can predict whether a customer will churn in the foreseeable future and assist enterprises to identify effects and possible causes for churn and subsequently use that knowledge to apply tailored incentives. This paper proposes a framework using a deep feedforward neural network for classification accompanied by a sequential pattern mining method on high-dimensional sparse data. We also propose a causal Bayesian network to predict cause probabilities that lead to customer churn. Evaluation metrics on test data confirm the XGBoost and our deep learning model outperformed previous techniques. Experimental analysis confirms that some independent causal variables representing the level of super guarantee contribution, account growth, and customer tenure were identified as confounding factors for customer churn with a high degree of belief. This paper provides a real-world customer churn analysis from current status inference to future directions in local superannuation funds.

Consumers rely on telco services for just about everything. It serves as a lifeline for healthcare providing telehealth to communicate with the chronically ill; it is the primary enabler of home schoolers accessing curriculum and collaborating with teachers and other students not enrolled in traditional school. The primary role of telco services, providing entertainment and connecting families and friends, is critical to the quality of life. Telcos enable small businesses to look big and enable big businesses to stay connected with suppliers and customers alike. Consumers are also diverse in age, gender, education, ethnicity, and socio-economic backgrounds – but they all have one thing in common.