The proliferation of big data across domains, from banking to health care to environmental monitoring, has spurred increasing demand for machine learning tools that help organizations make decisions based on the data they gather. That growing industry demand has driven researchers to explore the possibilities of automated machine learning (AutoML), which seeks to automate the development of machine learning solutions in order to make them accessible for nonexperts, improve their efficiency, and accelerate machine learning research. For example, an AutoML system might enable doctors to use their expertise interpreting electroencephalography (EEG) results to build a model that can predict which patients are at higher risk for epilepsy -- without requiring the doctors to have a background in data science. Yet, despite more than a decade of work, researchers have been unable to fully automate all steps in the machine learning development process. Even the most efficient commercial AutoML systems still require a prolonged back-and-forth between a domain expert, like a marketing manager or mechanical engineer, and a data scientist, making the process inefficient.

In video reviews of the latest drone models to his 80,000 YouTube subscribers, Indiana college student Carson Miller doesn't seem like an unwitting tool of Chinese spies. Yet that's how the U.S. is increasingly viewing him and thousands of other Americans who purchase drones built by Shenzhen-based SZ DJI Technology Co., the world's top producer of unmanned aerial vehicles. Miller, who bought his first DJI model in 2016 for $500 and now owns six of them, shows why the company controls more than half of the U.S. drone market. "If tomorrow DJI were completely banned," the 21-year-old said, "I would be pretty frightened." Critics of DJI warn the dronemaker may be channeling reams of sensitive data to Chinese intelligence agencies on everything from critical infrastructure like bridges and dams to personal information such as heart rates and facial recognition.

In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. Various representations of code in terms of tokens, syntax trees, dependency graphs, code navigation paths, or a combination of their variants have been proposed, however, existing vanilla learning techniques have a major limitation in robustness, i.e., it is easy for the models to make incorrect predictions when the inputs are altered in a subtle way. To enhance the robustness, existing approaches focus on recognizing adversarial samples rather than on the valid samples that fall outside a given distribution, which we refer to as out-of-distribution (OOD) samples. Recognizing such OOD samples is the novel problem investigated in this paper. To this end, we propose to first augment the in=distribution datasets with out-of-distribution samples such that, when trained together, they will enhance the model's robustness. We propose the use of an energy-bounded learning objective function to assign a higher score to in-distribution samples and a lower score to out-of-distribution samples in order to incorporate such out-of-distribution samples into the training process of source code models. In terms of OOD detection and adversarial samples detection, our evaluation results demonstrate a greater robustness for existing source code models to become more accurate at recognizing OOD data while being more resistant to adversarial attacks at the same time. Furthermore, the proposed energy-bounded score outperforms all existing OOD detection scores by a large margin, including the softmax confidence score, the Mahalanobis score, and ODIN.

Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. When does this hold true, and which algorithmic components are necessary? Through extensive experiments, we boil supervised learning for offline RL down to its essential elements. In every environment suite we consider, simply maximizing likelihood with a two-layer feedforward MLP is competitive with state-of-the-art results of substantially more complex methods based on TD learning or sequence modeling with Transformers. Carefully choosing model capacity (e.g., via regularization or architecture) and choosing which information to condition on (e.g., goals or rewards) are critical for performance. These insights serve as a field guide for practitioners doing Reinforcement Learning via Supervised Learning (which we coin RvS learning). They also probe the limits of existing RvS methods, which are comparatively weak on random data, and suggest a number of open problems. Offline and off-policy reinforcement learning (RL) are typically addressed using value-based methods. While theoretically appealing because they include performance guarantees under certain assumptions [27], such methods can be difficult to apply in practice; they tend to require complex tricks to stabilize learning and delicate tuning of many hyperparameters. Recent work has explored an alternative approach: convert the RL problem into a conditional, filtered, or weighted imitation learning problem.

Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning. However, most self-supervised and deep clustering techniques rely heavily on data augmentation, rendering them ineffective for many learning tasks where insufficient domain knowledge exists for performing augmentation. We propose a new self-distillation based algorithm for domain-agnostic clustering. Our method builds upon the existing deep clustering frameworks and requires no separate student model. The proposed method outperforms existing domain agnostic (augmentation-free) algorithms on CIFAR-10. We empirically demonstrate that knowledge distillation can improve unsupervised representation learning by extracting richer `dark knowledge' from the model than using predicted labels alone. Preliminary experiments also suggest that self-distillation improves the convergence of DeepCluster-v2.

Covid-19 enforced countries to adopt online or hybrid learning in order to catch up to expected learning targets. Yet, many countries remain inefficient at moving to online or hybrid education. Also, though some countries manage to boost students progress (like Italy increased their progress with online tutoring by 4.7 % compared to traditional schooling), some others fail to generate the same outcome from the online learning. However, recently, education industry leaders have started identifying use cases of process mining to improve online learning platforms, teaching methodologies and learning habits of students. In this article, we explain what is educational process mining, what are the use cases, benefits and challenges of applying process mining to educational domains.

The course indeed lived up to it what it said in the beginning. The course exposes oneself to the various real-life applications of Machine Learning a

This decoupling had baleful economic and social consequences: low paid, insecure jobs held by non-college workers; low participation rates in the labor force; weak upward mobility across generations; and festering earnings and employment disparities among races that have not substantially improved in decades. While new technologies have contributed to these poor results, these outcomes were not an inevitable consequence of technological change, nor of globalization, nor of market forces. Similar pressures from digitalization and globalization affected most industrialized countries, and yet their labor markets fared better."

Recently, my content crossed 100,000 views. I've been writing for about a year (and really picked up consistency over this summer). I never expected this level of viewership or the positive reception my work has gotten. Therefore, this was quite a surprise to me. It got me thinking about my AI/ML/Tech journey.

Providing appropriate questions according to a student's knowledge level is imperative in personalized learning. However, It requires a lot of manual effort for teachers to understand students' knowledge status and provide optimal questions accordingly. To address this problem, we introduce a question scheduling model that can effectively boost student knowledge level using Reinforcement Learning (RL). Our proposed method first evaluates students' concept-level knowledge using knowledge tracing (KT) model. Given predicted student knowledge, RL-based recommender predicts the benefits of each question. With curriculum range restriction and duplicate penalty, the recommender selects questions sequentially until it reaches the predefined number of questions. In an experimental setting using a student simulator, which gives 20 questions per day for two weeks, questions recommended by the proposed method increased average student knowledge level by 21.3%, superior to an expert-designed schedule baseline with a 10% increase in student knowledge levels.