This report summarizes the work carried out by the authors during the Twelfth Montreal Industrial Problem Solving Workshop, held at Université de Montréal in August 2022. The team tackled a problem submitted by CBC/Radio-Canada on the theme of Automatic Text Simplification (ATS). In order to make its written content more widely accessible, and to support its second-language teaching activities, CBC/RC has recently been exploring the potential of automatic methods to simplify texts. They have developed a modular lexical simplification system (LSS), which identifies complex words in French and English texts, and replaces them with simpler, more common equivalents. Recently however, the ATS research community has proposed a number of approaches that rely on deep learning methods to perform more elaborate transformations, not limited to just lexical substitutions, but covering syntactic restructuring and conceptual simplifications as well.

Machine learning may be a form of computing that permits computers to be told and build selections while not being expressly programmed. It involves the employment of algorithms and applied mathematics models to investigate and build predictions or selections supported knowledge. The model makes predictions supported by patterns it's learned from the coaching knowledge. The model should discover the underlying structure within the knowledge on its own. The model learns through trial and error, adjusting its actions to support the outcomes it receives.

Teachers are a creative bunch. They have to be to come up with lesson plans and exams that help students grow their minds and prevent those same students from relying too much on technology to enhance their work or to cheat. Which is why the rollout of OpenAI's ChatGPT has many teachers worried. The chatbot can answer almost any type of question, even if the answers aren't always accurate. Marketplace's Kimberly Adams spoke with Daniel Herman, an English teacher at Maybeck High School in Berkeley, California.

Organizations need skilled, forward-thinking Big Data practitioners who can apply their business and technical skills to unstructured data such as tweets, posts, pictures, audio files, videos, sensor data, and satellite imagery and more to identify behaviors and preferences of prospects, clients, competitors, and others. In this short course you'll gain practical skills when you learn how to work with Apache Spark for Data Engineering and Machine Learning (ML) applications. You will work hands-on with Spark MLlib, Spark Structured Streaming, and more to perform extract, transform and load (ETL) tasks as well as Regression, Classification, and Clustering. The course culminates in a project where you will apply your Spark skills to an ETL for ML workflow use-case. NOTE: This course requires that you have foundational skills for working with Apache Spark and Jupyter Notebooks.

In this course, we'll make predictions on product usage and calculate optimal safety stock storage. We'll start with a time series of shoe sales across multiple stores on three different continents. To begin, we'll look for unique insights and other interesting things we can find in the data by performing groupings and comparing products within each store. Then, we'll use a seasonal autoregressive integrated moving average (SARIMA) model to make predictions on future sales. In addition to making predictions, we'll analyze the provided statistics (such as p-score) to judge the viability of using the SARIMA model to make predictions.

In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained stochastic optimization problems, with the constraints originating mainly from model assumptions that define a trade-off between complexity and performance. This trade-off is closely related to over-fitting, generalization capacity, and robustness to noise and adversarial attacks, and depends on both the structure and complexity of the model, as well as the properties of the optimization methods used. We develop an online prototype-based learning algorithm based on annealing optimization that is formulated as an online gradient-free stochastic approximation algorithm. The learning model can be viewed as an interpretable and progressively growing competitive-learning neural network model to be used for supervised, unsupervised, and reinforcement learning. The annealing nature of the algorithm contributes to minimal hyper-parameter tuning requirements, poor local minima prevention, and robustness with respect to the initial conditions. At the same time, it provides online control over the performance-complexity trade-off by progressively increasing the complexity of the learning model as needed, through an intuitive bifurcation phenomenon. Finally, the use of stochastic approximation enables the study of the convergence of the learning algorithm through mathematical tools from dynamical systems and control, and allows for its integration with reinforcement learning algorithms, constructing an adaptive state-action aggregation scheme.

Despite its great success, backpropagation has certain limitations that necessitate the investigation of new learning methods. In this study, we present a biologically plausible local learning rule that improves upon Hebb's well-known proposal and discovers unsupervised features by local competitions among neurons. This simple learning rule enables the creation of a forward learning paradigm called activation learning, in which the output activation (sum of the squared output) of the neural network estimates the likelihood of the input patterns, or "learn more, activate more" in simpler terms. For classification on a few small classical datasets, activation learning performs comparably to backpropagation using a fully connected network, and outperforms backpropagation when there are fewer training samples or unpredictable disturbances. Additionally, the same trained network can be used for a variety of tasks, including image generation and completion. Activation learning also achieves state-of-the-art performance on several real-world datasets for anomaly detection. This new learning paradigm, which has the potential to unify supervised, unsupervised, and semi-supervised learning and is reasonably more resistant to adversarial attacks, deserves in-depth investigation. The backpropagation algorithm [1] has driven the recent success of machine learning in tasks such as speech and image recognition [2], language processing, image and music creation, playing human games [3], etc. Many scientists argue that the backpropagation algorithm, despite being a highly effective tool for training neural networks by minimizing specific loss functions, is different from the rules governing human learning [4]-[7]. One limitation of backpropagation is that the features learned by minimizing a particular loss function tend to be task-specific. This makes it difficult for the trained models to perform generic tasks, necessitates a large amount of labeled data, and renders them vulnerable to adversarial attacks [8]. Inspired by the brain, which is believed to learn in a predominantly unsupervised fashion [9], [10], we intend to create a new learning paradigm that enables forward unsupervised training of neural networks based on a simple local learning rule while achieving comparable performance to backpropagation. The fundamental idea is that, when every neuron in a layer competes to activate while presenting distinct features, the network transmits the maximum amount of information to the next layer, and learning is enforced. Hebbian plasticity is a local correlation-based learning rule proposed by Hebb that has been supported by experimental evidences such as long-term potentiation and depression [5], [11]. It is simply phrased as'cells that fire together wire together.' H. Zhou is with the School of Information Science and Engineering, Shandong University, Qingdao, Shandong, 266237 China.

In a sequential decision-making problem, having a structural dependency amongst the reward distributions associated with the arms makes it challenging to identify a subset of alternatives that guarantees the optimal collective outcome. Thus, besides individual actions' reward, learning the causal relations is essential to improve the decision-making strategy. To solve the two-fold learning problem described above, we develop the 'combinatorial semi-bandit framework with causally related rewards', where we model the causal relations by a directed graph in a stationary structural equation model. The nodal observation in the graph signal comprises the corresponding base arm's instantaneous reward and an additional term resulting from the causal influences of other base arms' rewards. The objective is to maximize the long-term average payoff, which is a linear function of the base arms' rewards and depends strongly on the network topology. To achieve this objective, we propose a policy that determines the causal relations by learning the network's topology and simultaneously exploits this knowledge to optimize the decision-making process. We establish a sublinear regret bound for the proposed algorithm. Numerical experiments using synthetic and real-world datasets demonstrate the superior performance of our proposed method compared to several benchmarks.

We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating one kind of bias by incorporating complex fairness-driven constraints into optimization objectives or designing additional layers that focus on specific protected attributes. We introduce a simple and generic bias mitigation approach that prevents models from learning relationships between protected attributes and output variable by reducing mutual information between them. We demonstrate that our approach is effective in reducing bias with little or no drop in accuracy. We also show that the models trained with our learning framework become causally fair and insensitive to the values of protected attributes. Finally, we validate our approach by studying feature interactions between protected and non-protected attributes. We demonstrate that these interactions are significantly reduced when applying our bias mitigation.

Federated Learning (FL) has been widely accepted as the solution for privacy-preserving machine learning without collecting raw data. While new technologies proposed in the past few years do evolve the FL area, unfortunately, the evaluation results presented in these works fall short in integrity and are hardly comparable because of the inconsistent evaluation metrics and experimental settings. In this paper, we propose a holistic evaluation framework for FL called FedEval, and present a benchmarking study on seven state-of-the-art FL algorithms. Specifically, we first introduce the core evaluation taxonomy model, called FedEval-Core, which covers four essential evaluation aspects for FL: Privacy, Robustness, Effectiveness, and Efficiency, with various well-defined metrics and experimental settings. Based on the FedEval-Core, we further develop an FL evaluation platform with standardized evaluation settings and easy-to-use interfaces. We then provide an in-depth benchmarking study between the seven well-known FL algorithms, including FedSGD, FedAvg, FedProx, FedOpt, FedSTC, SecAgg, and HEAgg. We comprehensively analyze the advantages and disadvantages of these algorithms and further identify the suitable practical scenarios for different algorithms, which is rarely done by prior work. Lastly, we excavate a set of take-away insights and future research directions, which are very helpful for researchers in the FL area.