We study the problem of active learning with the added twist that the learner is assisted by a helpful teacher. We consider the following natural interaction protocol: At each round, the learner proposes a query asking for the label of an instance $x^q$, the teacher provides the requested label $\{x^q, y^q\}$ along with explanatory information to guide the learning process. In this paper, we view this information in the form of an additional contrastive example ($\{x^c, y^c\}$) where $x^c$ is picked from a set constrained by $x^q$ (e.g., dissimilar instances with the same label). Our focus is to design a teaching algorithm that can provide an informative sequence of contrastive examples to the learner to speed up the learning process. We show that this leads to a challenging sequence optimization problem where the algorithm's choices at a given round depend on the history of interactions. We investigate an efficient teaching algorithm that adaptively picks these contrastive examples. We derive strong performance guarantees for our algorithm based on two problem-dependent parameters and further show that for specific types of active learners (e.g., a generalized binary search learner), the proposed teaching algorithm exhibits strong approximation guarantees. Finally, we illustrate our bounds and demonstrate the effectiveness of our teaching framework via two numerical case studies.

Quantum computing has promised significant improvement in solving difficult computational tasks over classical computers. Designing quantum circuits for practical use, however, is not a trivial objective and requires expert-level knowledge. To aid this endeavor, this paper proposes a machine learning-based method to construct quantum circuit architectures. Previous works have demonstrated that classical deep reinforcement learning (DRL) algorithms can successfully construct quantum circuit architectures without encoded physics knowledge. However, these DRL-based works are not generalizable to settings with changing device noises, thus requiring considerable amounts of training resources to keep the RL models up-to-date. With this in mind, we incorporated continual learning to enhance the performance of our algorithm. In this paper, we present the Probabilistic Policy Reuse with deep Q-learning (PPR-DQL) framework to tackle this circuit design challenge. By conducting numerical simulations over various noise patterns, we demonstrate that the RL agent with PPR was able to find the quantum gate sequence to generate the two-qubit Bell state faster than the agent that was trained from scratch. The proposed framework is general and can be applied to other quantum gate synthesis or control problems -- including the automatic calibration of quantum devices.

Contrastive learning has been proven suitable for learning sentence embeddings and can significantly improve the semantic textual similarity (STS) tasks. Recently, large contrastive learning models, e.g., Sentence-T5, tend to be proposed to learn more powerful sentence embeddings. Though effective, such large models are hard to serve online due to computational resources or time cost limits. To tackle that, knowledge distillation (KD) is commonly adopted, which can compress a large "teacher" model into a small "student" model but generally suffer from some performance loss. Here we propose an enhanced KD framework termed Distill-Contrast (DisCo). The proposed DisCo framework firstly utilizes KD to transfer the capability of a large sentence embedding model to a small student model on large unlabelled data, and then finetunes the student model with contrastive learning on labelled training data. For the KD process in DisCo, we further propose Contrastive Knowledge Distillation (CKD) to enhance the consistencies among teacher model training, KD, and student model finetuning, which can probably improve performance like prompt learning. Extensive experiments on 7 STS benchmarks show that student models trained with the proposed DisCo and CKD suffer from little or even no performance loss and consistently outperform the corresponding counterparts of the same parameter size. Amazingly, our 110M student model can even outperform the latest state-of-the-art (SOTA) model, i.e., Sentence-T5(11B), with only 1% parameters.

I am pleased to present to you this Guide to our plans for the upcoming fall semester and reopening of our campuses. In form and in content, this coming semester will be like no other. We will live differently, work differently and learn differently. But in its very difference rests its enormous power. The mission of Yeshiva University is to enrich the moral, intellectual and spiritual development of each of our students, empowering them with the knowledge and abilities to become people of impact and leaders of tomorrow.

Kavli Foundation President Cynthia Friend (front row center) and Director of Public Engagement Brooke Smith (second row right) visited UC Berkeley in November to discuss the new Kavli Center with campus researchers. Every day, algorithms select which news stories appear in our social media feeds. Airplanes allow global travel at nearly the speed of sound while emitting greenhouse gases that accelerate the impacts of climate change. And recent advances in DNA sequencing and editing enable us to understand our fundamental genetic programming -- and potentially change it. While it may be challenging to anticipate where science might lead us next, researchers at the University of California, Berkeley, are taking steps to ensure that the public has a greater say in future scientific advances, and that questions of ethics and social equity take a prominent role in scientific decision-making. UC Berkeley announced today that the campus will be home to a new Kavli Center for Ethics, Science, and the Public, which, alongside a second center at the University of Cambridge in the United Kingdom, will connect scientists, ethicists, social scientists, science communicators and the public in necessary and intentional discussions about the potential impacts of scientific discoveries.

Depth estimation is one of the fundamental problems in computer vision, and it's essential for a wide range of applications, such as robotic vision or surgical navigation. Various deep learning-based approaches have been developed to provide end-to-end solutions for depth and disparity estimation in recent times. One such method is self-supervised monocular depth estimation. Monocular depth estimation is the process of determining scene depth from a single image. For disparity estimation, the bulk of these models use a U-Net-based design.

Machine learning specialized libraries and frameworks are available in a large number of Python distributions, making the development process easier and decreasing development time. Python's straightforward syntax and readability enable it to be used for fast testing of complicated algorithms while also making it accessible to those who are not programmers. Data science with Python is made simpler by the availability of a plethora of libraries, such as NumPy, Pandas, and Matplotlib, which facilitate data cleaning, data analysis, data visualization, and machine learning activities. In data analysis using python python's ability to create and manage data structures quickly, for example, is one of the most common applications of the language in data analysis -- Pandas, for example, provides a plethora of tools for manipulating, analyzing, and even representing complex datasets -- and this is one of the most common applications of Python in data analysis. We had a team people editing and marketing the course, the editing was done by Mohammad Chowdhury and the marketing was done by Mohammad Fahmid Chowdhury. The course was created by professors with years of Python experience. The course content was created by Matt Williams, he is a professor with years of Python and Data Science experience, under the CC Attribution license.

It's Monday morning of some week in 2050 and you're shuffling into your kitchen, drawn by the smell of fresh coffee C-3PO has brewed while he unloaded the dishwasher. "Here you go, Han Solo, I used the new flavor you bought yesterday," C-3PO tells you as he hands you the cup. C-3PO arrived barely a month ago and already has developed a wonderful sense of humor and even some snark. He isn't the real C-3PO, of course--you just named him that because you are a vintage movie buff--but he's the latest NeuroCyber model that comes closest to how people think, talk, and acquire knowledge. He's no match to the original C-3PO's fluency in 6 million forms of communication, but he's got full linguistic mastery and can learn from humans like humans do--from observation and imitation, whether it's using sarcasm or sticking dishes into slots. Unlike the early models of such assistants like Siri or Alexa who could recognize commands and act upon them, NeuroCybers can evolve into intuitive assistants and companions.

I have been studying reinforcement learning since November 2018 when I learned what is was during my time with Insight Data Science. I was an artificial intelligence fellow and I was so fascinated by this idea that you could simulate an environment and get an agent to learn an optimal policy to maximize rewards from that environment. The more I read about RL the more I noticed men were using RL to either train robots or using it to create and play video games. I thought this was such a whack idea! Robots are really cool but reinforcement learning could be used for so much more, I just didn't have any examples of how it could be done yet so I imagined one possibility for using reinforcement learning in an educational environment.

Retention of students is an issue for academic institutions across the globe, given limited resources and tight budgets. In some countries, the average dropout rate is around 45%. Accordingly, measures are being taken to find a solution to this problem. Experts say that such strategies are most effective if applied in a student's first year of the opted course. The importance of artificial intelligence (AI) and machine learning (ML) can be vital here. Using AI-enabled devices, instructors can suit everyone's needs and requirements on a case-by-case basis which means each learner gets desired attention.