Both conceptual modeling and machine learning have long been recognized as important areas of research. With the increasing emphasis on digitizing and processing large amounts of data for business and other applications, it would be helpful to consider how these areas of research can complement each other. To understand how they can be paired, we provide an overview of machine learning foundations and development cycle. We then examine how conceptual modeling can be applied to machine learning and propose a framework for incorporating conceptual modeling into data science projects. The framework is illustrated by applying it to a healthcare application. For the inverse pairing, machine learning can impact conceptual modeling through text and rule mining, as well as knowledge graphs. The pairing of conceptual modeling and machine learning in this this way should help lay the foundations for future research.

We propose a method to easily modify existing offline Recommender Systems to run online using Transfer Learning. Online Learning for Recommender Systems has two main advantages: quality and scale. Like many Machine Learning algorithms in production if not regularly retrained will suffer from Concept Drift. A policy that is updated frequently online can adapt to drift faster than a batch system. This is especially true for user-interaction systems like recommenders where the underlying distribution can shift drastically to follow user behaviour. As a platform grows rapidly like Grubhub, the cost of running batch training jobs becomes material. A shift from stateless batch learning offline to stateful incremental learning online can recover, for example, at Grubhub, up to a 45x cost savings and a +20% metrics increase. There are a few challenges to overcome with the transition to online stateful learning, namely convergence, non-stationary embeddings and off-policy evaluation, which we explore from our experiences running this system in production.

The Software Report is pleased to announce The Top 100 Software Companies of 2021. This year's awardee list is comprised of a wide range of companies from the most well-known such as Microsoft, Adobe, and Salesforce to the relatively newer but rapidly growing - Qualtrics, Atlassian, and Asana. A good number of awardees may be new names to some but that should be no surprise given software has always been an industry of startups that seemingly came out of nowhere to create and dominate a new space. Software has become the backbone of our economy. From large enterprises to small businesses, most all rely on software whether for accounting, marketing, sales, supply chain, or a myriad of other functions. Software has become the dominant industry of our time and as such, we place a significance on highlighting the best companies leading the industry forward. The following awardees were nominated and selected based on a thorough evaluation process. Among the key criteria considered were ...

In what may be a sign of the times, Levi Strauss & Co. launched a first for the denim company: an artificial intelligence and machine learning bootcamp. But this one's not necessarily just for its engineers or tech developers -- it's also for the nontechie set in areas, like retail. Started in May 2021, the program saw its first wave of students graduate and take their training to different areas of the organization. The company marked the moment in a blog post published Tuesday. In it, Levi's described the Machine Learning Bootcamp as "an intensive, full-time, fully paid eight-week training program where [participants] left their day-to-day jobs to complete this unique program. In the bootcamp's inaugural cohort, we trained more than 40 employees -- 63 percent of whom were female, representing 14 locations around the world with employees from corporate, retail stores, distribution centers, and data centers."

Most machine learning algorithms are configured by one or several hyperparameters that must be carefully chosen and often considerably impact performance. To avoid a time consuming and unreproducible manual trial-and-error process to find well-performing hyperparameter configurations, various automatic hyperparameter optimization (HPO) methods, e.g., based on resampling error estimation for supervised machine learning, can be employed. After introducing HPO from a general perspective, this paper reviews important HPO methods such as grid or random search, evolutionary algorithms, Bayesian optimization, Hyperband and racing. It gives practical recommendations regarding important choices to be made when conducting HPO, including the HPO algorithms themselves, performance evaluation, how to combine HPO with ML pipelines, runtime improvements, and parallelization.

This paper presents a deep learning approach for the classification of Engineering (CAD) models using Convolutional Neural Networks (CNNs). Owing to the availability of large annotated datasets and also enough computational power in the form of GPUs, many deep learning-based solutions for object classification have been proposed of late, especially in the domain of images and graphical models. Nevertheless, very few solutions have been proposed for the task of functional classification of CAD models. Hence, for this research, CAD models have been collected from Engineering Shape Benchmark (ESB), National Design Repository (NDR) and augmented with newer models created using a modelling software to form a dataset - 'CADNET'. It is proposed to use a residual network architecture for CADNET, inspired by the popular ResNet. A weighted Light Field Descriptor (LFD) scheme is chosen as the method of feature extraction, and the generated images are fed as inputs to the CNN. The problem of class imbalance in the dataset is addressed using a class weights approach. Experiments have been conducted with other signatures such as geodesic distance etc. using deep networks as well as other network architectures on the CADNET. The LFD-based CNN approach using the proposed network architecture, along with gradient boosting yielded the best classification accuracy on CADNET.

The world of empirical machine learning (ML) strongly relies on benchmarks in order to determine the relative effectiveness of different algorithms and methods. This paper proposes the notion of "a benchmark lottery" that describes the overall fragility of the ML benchmarking process. The benchmark lottery postulates that many factors, other than fundamental algorithmic superiority, may lead to a method being perceived as superior. On multiple benchmark setups that are prevalent in the ML community, we show that the relative performance of algorithms may be altered significantly simply by choosing different benchmark tasks, highlighting the fragility of the current paradigms and potential fallacious interpretation derived from benchmarking ML methods. Given that every benchmark makes a statement about what it perceives to be important, we argue that this might lead to biased progress in the community. We discuss the implications of the observed phenomena and provide recommendations on mitigating them using multiple machine learning domains and communities as use cases, including natural language processing, computer vision, information retrieval, recommender systems, and reinforcement learning.

In many applications of AI, the algorithm's output is framed as a suggestion to a human user. The user may ignore the advice or take it into consideration to modify his/her decisions. With the increasing prevalence of such human-AI interactions, it is important to understand how users act (or do not act) upon AI advice, and how users regard advice differently if they believe the advice come from an "AI" versus another human. In this paper, we characterize how humans use AI suggestions relative to equivalent suggestions from a group of peer humans across several experimental settings. We find that participants' beliefs about the human versus AI performance on a given task affects whether or not they heed the advice. When participants decide to use the advice, they do so similarly for human and AI suggestions. These results provide insights into factors that affect human-AI interactions.

Automated writing evaluation systems can improve students' writing insofar as students attend to the feedback provided and revise their essay drafts in ways aligned with such feedback. Existing research on revision of argumentative writing in such systems, however, has focused on the types of revisions students make (e.g., surface vs. content) rather than the extent to which revisions actually respond to the feedback provided and improve the essay. We introduce an annotation scheme to capture the nature of sentence-level revisions of evidence use and reasoning (the `RER' scheme) and apply it to 5th- and 6th-grade students' argumentative essays. We show that reliable manual annotation can be achieved and that revision annotations correlate with a holistic assessment of essay improvement in line with the feedback provided. Furthermore, we explore the feasibility of automatically classifying revisions according to our scheme.

The mainstream approach for filter pruning is usually either to force a hard-coded importance estimation upon a computation-heavy pretrained model to select "important" filters, or to impose a hyperparameter-sensitive sparse constraint on the loss objective to regularize the network training. In this paper, we present a novel filter pruning method, dubbed dynamic-coded filter fusion (DCFF), to derive compact CNNs in a computation-economical and regularization-free manner for efficient image classification. Each filter in our DCFF is firstly given an inter-similarity distribution with a temperature parameter as a filter proxy, on top of which, a fresh Kullback-Leibler divergence based dynamic-coded criterion is proposed to evaluate the filter importance. In contrast to simply keeping high-score filters in other methods, we propose the concept of filter fusion, i.e., the weighted averages using the assigned proxies, as our preserved filters. We obtain a one-hot inter-similarity distribution as the temperature parameter approaches infinity. Thus, the relative importance of each filter can vary along with the training of the compact CNN, leading to dynamically changeable fused filters without both the dependency on the pretrained model and the introduction of sparse constraints. Extensive experiments on classification benchmarks demonstrate the superiority of our DCFF over the compared counterparts. For example, our DCFF derives a compact VGGNet-16 with only 72.77M FLOPs and 1.06M parameters while reaching top-1 accuracy of 93.47% on CIFAR-10. A compact ResNet-50 is obtained with 63.8% FLOPs and 58.6% parameter reductions, retaining 75.60% top-1 accuracy on ILSVRC-2012. Our code, narrower models and training logs are available at https://github.com/lmbxmu/DCFF.