In this paper, we consider a challenging but realistic continual learning (CL) problem, Few-Shot Continual Active Learning (FoCAL), where a CL agent is provided with unlabeled data for a new or a previously learned task in each increment and the agent only has limited labeling budget available. Towards this, we build on the continual learning and active learning literature and develop a framework that can allow a CL agent to continually learn new object classes from a few labeled training examples. Our framework represents each object class using a uniform Gaussian mixture model (GMM) and uses pseudo-rehearsal to mitigate catastrophic forgetting. The framework also uses uncertainty measures on the Gaussian representations of the previously learned classes to find the most informative samples to be labeled in an increment. We evaluate our approach on the CORe-50 dataset and on a real humanoid robot for the object classification task. The results show that our approach not only produces state-of-the-art results on the dataset but also allows a real robot to continually learn unseen objects in a real environment with limited labeling supervision provided by its user.

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student models, it is commonly believed that a high performing teacher is preferred. Consequently, practitioners tend to use a well trained network or an ensemble of them as the teacher. In this paper, we make an intriguing observation that an intermediate model, i.e., a checkpoint in the middle of the training procedure, often serves as a better teacher compared to the fully converged model, although the former has much lower accuracy. More surprisingly, a weak snapshot ensemble of several intermediate models from a same training trajectory can outperform a strong ensemble of independently trained and fully converged models, when they are used as teachers. We show that this phenomenon can be partially explained by the information bottleneck principle: the feature representations of intermediate models can have higher mutual information regarding the input, and thus contain more "dark knowledge" for effective distillation. We further propose an optimal intermediate teacher selection algorithm based on maximizing the total task-related mutual information. Experiments verify its effectiveness and applicability.

The old empathetic adage, ``Walk a mile in their shoes,'' asks that one imagine the difficulties others may face. This suggests a new ML counterfactual fairness criterion, based on a \textit{group} level: How would members of a nonprotected group fare if their group were subject to conditions in some protected group? Instead of asking what sentence would a particular Caucasian convict receive if he were Black, take that notion to entire groups; e.g. how would the average sentence for all White convicts change if they were Black, but with their same White characteristics, e.g. same number of prior convictions? We frame the problem and study it empirically, for different datasets. Our approach also is a solution to the problem of covariate correlation with sensitive attributes.

We introduce a high-quality dataset that contains 3,397 samples comprising (i) multiple choice questions, (ii) answers (including distractors), and (iii) their source documents, from the educational domain. Each question is phrased in two forms, normal and close. Correct answers are linked to source documents with sentence-level annotations. Thus, our versatile dataset can be used for both question and distractor generation, as well as to explore new challenges such as question format conversion. Furthermore, 903 questions are accompanied by their cognitive complexity level as per Bloom's taxonomy. All questions have been generated by educational experts rather than crowd workers to ensure they are maintaining educational and learning standards. Our analysis and experiments suggest distinguishable differences between our dataset and commonly used ones for question generation for educational purposes. We believe this new dataset can serve as a valuable resource for research and evaluation in the educational domain. The dataset and baselines will be released to support further research in question generation.

We study an algorithmic equivalence technique between non-convex gradient descent and convex mirror descent. We start by looking at a harder problem of regret minimization in online non-convex optimization. We show that under certain geometric and smoothness conditions, online gradient descent applied to non-convex functions is an approximation of online mirror descent applied to convex functions under reparameterization. In continuous time, the gradient flow with this reparameterization was shown to be exactly equivalent to continuous-time mirror descent by Amid and Warmuth 2020, but theory for the analogous discrete time algorithms is left as an open problem. We prove an $O(T^{\frac{2}{3}})$ regret bound for non-convex online gradient descent in this setting, answering this open problem. Our analysis is based on a new and simple algorithmic equivalence method.

Mike Chapple is Teaching Professor of IT, Analytics, and Operations at the University of Notre Dame's Mendoza College of Business where he teaches graduate and undergraduate courses in cybersecurity and business analytics. Prior to joining Notre Dame's faculty, Mike served as Senior Director for IT Service Delivery at the University. In this role, he oversaw the information security, IT compliance, cloud computing, data governance, IT architecture, learning platforms, project management, strategic planning and product management functions for the Office of Information Technologies. Mike led Notre Dame's Cloud First strategy which moved 80% of the institution's IT services into the cloud over three years. Mike previously served as Senior Advisor to the Executive Vice President at Notre Dame for two years.

We've seen AIs create music, pornography and art. The Estonian startup Yummy started off creating a meal-kit startup, but along the way created an AI that can create and adapt recipes based on your taste and dietary restrictions, complete with AI-generated images of what your dishes might look like. "Imagine a world where you would not have to spend years of your life on deciding what to eat, search for recipes, research nutritional information and health benefits, follow diets and do grocery shopping," says co-founder and CEO Martin Salo in an interview with TechCrunch. "Imagine we solve this complex problem on your behalf, based on your personal preferences -- and got it right every time." The co-founders of the company started Clean Kitchen together in Estonia back in 2020.

Back in sixth grade, I was a robot. Or at least, that's what I told anyone who asked--in reality, my 11-year-old self was completely human. In 2018, I was diagnosed with osteosarcoma, a rare bone cancer that meant nine months of chemotherapy and too many surgeries to count. It was a year punctuated with hospital visits, needle pokes, and days when I felt too nauseated to even look at a plate of food. And yet, my primary concern was that in my immunocompromised state, I was no longer able to attend school.

Role requiring'No experience data provided' months of experience in None

Percipient.ai is a proud equal opportunity employer and we are committed to hiring and supporting a diverse workforce. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. We believe in the benefit of a highly-collaborative, in-office culture, so if you're in the Bay Area or near the Reston Town Center, plan to be in the office 2-3 days a week.