We provide a regularization framework for subject transfer learning in which we seek to train an encoder and classifier to minimize classification loss, subject to a penalty measuring independence between the latent representation and the subject label. We introduce three notions of independence and corresponding penalty terms using mutual information or divergence as a proxy for independence. For each penalty term, we provide several concrete estimation algorithms, using analytic methods as well as neural critic functions. We provide a hands-off strategy for applying this diverse family of regularization algorithms to a new dataset, which we call "AutoTransfer". We evaluate the performance of these individual regularization strategies and our AutoTransfer method on EEG, EMG, and ECoG datasets, showing that these approaches can improve subject transfer learning for challenging real-world datasets. In this work, we investigate methods for transfer learning in the classification of biosignals data. Previous work has established the difficulty of transfer learning for biosignals and even the issue of so-called "negative transfer", in which naive attempts to combine datasets from multiple subjects or sessions can paradoxically decrease model performance, due to differences in response statistics [1, 2]. We address the problem of subject transfer by training models to be invariant to changes in a nuisance variable representing subject identifier.

Calorie and nutrition research has attained increased interest in recent years. But, due to the complexity of the problem, literature in this area focuses on a limited subset of ingredients or dish types and simple convolutional neural networks or traditional machine learning. Simultaneously, estimation of ingredient portions can help improve calorie estimation and meal re-production from a given image. In this paper, given a single cooking image, a pipeline for calorie estimation and meal re-production for different servings of the meal is proposed. The pipeline contains two stages. In the first stage, a set of ingredients associated with the meal in the given image are predicted. In the second stage, given image features and ingredients, portions of the ingredients and finally the total meal calorie are simultaneously estimated using a deep transformer-based model. Portion estimation introduced in the model helps improve calorie estimation and is also beneficial for meal re-production in different serving sizes. To demonstrate the benefits of the pipeline, the model can be used for meal kits generation. To evaluate the pipeline, the large scale dataset Recipe1M is used. Prior to experiments, the Recipe1M dataset is parsed and explicitly annotated with portions of ingredients. Experiments show that using ingredients and their portions significantly improves calorie estimation. Also, a visual interface is created in which a user can interact with the pipeline to reach accurate calorie estimations and generate a meal kit for cooking purposes.

Multiclass classification (MCC) is a fundamental machine learning problem which aims to classify each instance into one of a predefined set of classes. Given an instance, a classification model computes a score for each class, all of which are then used to sort the classes. The performance of a classification model is usually measured by Top-K Accuracy/Error (e.g., K=1 or 5). In this paper, we do not aim to propose new neural representation learning models as most recent works do, but to show that it is easy to boost MCC performance with a novel formulation through the lens of ranking. In particular, by viewing MCC as to rank classes for an instance, we first argue that ranking metrics, such as Normalized Discounted Cumulative Gain (NDCG), can be more informative than existing Top-K metrics. We further demonstrate that the dominant neural MCC architecture can be formulated as a neural ranking framework with a specific set of design choices. Based on such generalization, we show that it is straightforward and intuitive to leverage techniques from the rich information retrieval literature to improve the MCC performance out of the box. Extensive empirical results on both text and image classification tasks with diverse datasets and backbone models (e.g., BERT and ResNet for text and image classification) show the value of our proposed framework.

In this work, we explain the setup for a technical, graduate-level course on Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence (FACT-AI) at the University of Amsterdam, which teaches FACT-AI concepts through the lens of reproducibility. The focal point of the course is a group project based on reproducing existing FACT-AI algorithms from top AI conferences and writing a corresponding report. In the first iteration of the course, we created an open source repository with the code implementations from the group projects. In the second iteration, we encouraged students to submit their group projects to the Machine Learning Reproducibility Challenge, resulting in 9 reports from our course being accepted for publication in the ReScience journal. We reflect on our experience teaching the course over two years, where one year coincided with a global pandemic, and propose guidelines for teaching FACT-AI through reproducibility in graduate-level AI study programs. We hope this can be a useful resource for instructors who want to set up similar courses in the future.

We are seeking an Assistant Professor with a PhD in Marketing. The Business School is looking to strengthen the area of marketing strategy. Priority will be given to candidates conducting research on customer relationship management (CRM), with an emphasis on applying machine learning (ML) and artificial intelligence (AI) approaches. Candidates must, as a minimum, demonstrate the motivation and ability to publish in top-tier marketing journals (e.g., papers targeted or submitted to journals ranked 4 or higher in the Academic Journal Guide published by the Association of Business Schools) and to teach effectively (e.g., good student evaluations). The chosen candidate must also possess strong quantitative skills (e.g., significant graduate level training in econometrics and statistics) and have experience with advanced machine learning, including text analytics, and artificial intelligence applications (e.g., neural network). It is expected that you have a reflective and conscientious attitude towards your own teaching and supervision.

From the author of a world bestseller published in eleven languages, The Hundred-Page Machine Learning Book, this new book by Andriy Burkov is the most complete applied AI book out there. It is filled with best practices and design patterns of building reliable machine learning solutions that scale. Andriy Burkov has a Ph.D. in AI and is the leader of a machine learning team at Gartner. This book is based on Andriy's own 15 years of experience in solving problems with AI as well as on the published experience of the industry leaders. Here's what Cassie Kozyrkov, Chief Decision Scientist at Google tells about the book in the Foreword: "You're looking at one of the few true Applied Machine Learning books out there. That's right, you found one! A real applied needle in the haystack of research-oriented stuff. Excellent job, dear reader... unless what you were actually looking for is a book to help you learn the skills to design general-purpose algorithms, in which case I hope the author won't be too upset with me for telling you to flee now and go pick up pretty much any other machine learning book. The machine learning equivalent of a bumper guide to innovating in recipes to make food at scale. Since you haven't read the book yet, I'll put it in culinary terms: you'll need to figure out what's worth cooking / what the objectives are (decision-making and product management), understand the suppliers and the customers (domain expertise and business acumen), how to process ingredients at scale (data engineering and analysis), how to try many different ingredient-appliance combinations quickly to generate potential recipes (prototype phase ML engineering), how to check that the quality of the recipe is good enough to serve (statistics), how to turn a potential recipe into millions of dishes served efficiently (production phase ML engineering), and how to ensure that your dishes stay top-notch even if the delivery truck brings you a ton of potatoes instead of the rice you ordered (reliability engineering). This book is one of the few to offer perspectives on each step of the end-to-end process."

Artificial Intelligence has made a huge impact across industries and education is one of them. While on one hand, it has transformed the way schools and teachers perform their job, on the other hand, it has advanced the way students study. As per Market Research Engine, AI in education market will soon pass $5.80 billion in the coming three to four years at a development rate of 45%. How is the education industry getting revolutionized by AI? AI in the education sector has automated administrative operations and made the tasks of companies and professors simpler. Apart from handling the classrooms, teachers also had to deal with several administrative and organizational errands.

Artificial Intelligence has made a huge impact across industries and education is one of them. While on one hand, it has transformed the way schools and teachers perform their job, on the other hand, it has advanced the way students study. As per Market Research Engine, AI in education market will soon pass $5.80 billion in the coming three to four years at a development rate of 45%. How is the education industry getting revolutionized by AI? AI in the education sector has automated administrative operations and made the tasks of companies and professors simpler. Apart from handling the classrooms, teachers also had to deal with several administrative and organizational errands.

A sweeping new study finds that women are penalized for pursuing research perceived to be "feminized" – an implicit bias surprisingly strong in fields associated with women. For more than a decade, women have earned more doctoral degrees than men in the United States. Despite that, women still lag behind men in getting tenure, getting published and reaching leadership positions in academia. Much of the research into why that might be focuses on structural barriers and explicit prejudice. But a new study by a team of researchers at Stanford Graduate School of Education (GSE) finds a widespread implicit bias against academic work that simply seems feminine – even if it's not about women or gender specifically.

Throughout the evolution of humankind, we have always aimed to achieve things that make our life easier by freeing us from laborious tasks. Just take, for example, the invention of the wheel, which revolutionized how we transport things, then thousands of years later came the computer and the internet. Every generation, we are making progress with one ultimate aim: to make our lives easier. So at this age, we are at the threshold where Artificial Intelligence (AI) is taking over our lives and reducing manual labor by leaps and bounds. We have used AI to crunch numbers and solve problems from behind the screen to advance in defense technologies and space exploration.