If your eyes haven't rolled to the back of your head yet, then chances are you're reading this from the front porch of a double-wide trailer parked somewhere below the Mason Dixon with a glass of sweet tea in your hand and a coon dog at your feet. Or if, like me, you're a bit more progressed from the stereotype, you might be standing in front of a classroom of semi-attentive undergraduate students at a Southeastern research university making your best effort to bridge the ever-widening practical and theoretical gaps between old-world journalistic traditions and new-age neoliberal ideologies related to the function of human language in society. Instead of discussing "tips and tricks" for conducting adequate online research in the digital age, we spent the next two hours working as a group to uncover the context surrounding the claims, reconstruct a timeline of events, and offer our best critiques of all sides of the argument based on the evidence we accumulated. As a doctoral research fellow in the School of Journalism and Media at the University of North Carolina at Chapel Hill, it's easy for me to admit that Lamoine's claim fascinated and excited me. What Lamoine has done, in my view, is make clear that at the pinnacle of social intelligence exists a radically benevolent empathy for the collective human condition -- one that borders on the mystical or transcendent, and that we would do well to put to use for the common good.

The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient deployment also necessitates a large amount of (labeled or unlabeled) training data. In this paper, we propose the teacher-guided training (TGT) framework for training a high-quality compact model that leverages the knowledge acquired by pretrained generative models, while obviating the need to go through a large volume of data. TGT exploits the fact that the teacher has acquired a good representation of the underlying data domain, which typically corresponds to a much lower dimensional manifold than the input space. Furthermore, we can use the teacher to explore input space more efficiently through sampling or gradient-based methods; thus, making TGT especially attractive for limited data or long-tail settings. We formally capture this benefit of proposed data-domain exploration in our generalization bounds. We find that TGT can improve accuracy on several image classification benchmarks as well as a range of text classification and retrieval tasks.

"Simply Logical -- Intelligent Reasoning by Example" by Peter Flach was first published by John Wiley in 1994. It could be purchased as book-only or with a 3.5 inch diskette containing the SWI-Prolog programmes printed in the book (for various operating systems). In 2007 the copyright reverted back to the author at which point the book and programmes were made freely available online; the print version is no longer distributed through John Wiley publishers. In 2015, as a pilot, we ported most of the original book into an online, interactive website using SWI-Prolog's SWISH platform. Since then, we launched the Simply Logical open source organisation committed to maintaining a suite of freely available interactive online educational resources about Artificial Intelligence and Logic Programming with Prolog. With the advent of new educational technologies we were inspired to rebuild the book from the ground up using the Jupyter Book platform enhanced with a collection of bespoke plugins that implement, among other things, interactive SWI-Prolog code blocks that can be executed directly in a web browser. This new version is more modular, easier to maintain, and can be split into custom teaching modules, in addition to being modern-looking, visually appealing, and compatible with a range of (mobile) devices of varying screen sizes.

YouTube users looking for instructions for a specific task may spend a long time browsing content trying to find the right video that matches their needs. Creating a visual summary (abridged version of a video) provides viewers with a quick overview and massively reduces search time. In this work, we focus on summarizing instructional videos, an under-explored area of video summarization. In comparison to generic videos, instructional videos can be parsed into semantically meaningful segments that correspond to important steps of the demonstrated task. Existing video summarization datasets rely on manual frame-level annotations, making them subjective and limited in size. To overcome this, we first automatically generate pseudo summaries for a corpus of instructional videos by exploiting two key assumptions: (i) relevant steps are likely to appear in multiple videos of the same task (Task Relevance), and (ii) they are more likely to be described by the demonstrator verbally (Cross-Modal Saliency). We propose an instructional video summarization network that combines a context-aware temporal video encoder and a segment scoring transformer. Using pseudo summaries as weak supervision, our network constructs a visual summary for an instructional video given only video and transcribed speech. To evaluate our model, we collect a high-quality test set, WikiHow Summaries, by scraping WikiHow articles that contain video demonstrations and visual depictions of steps allowing us to obtain the ground-truth summaries. We outperform several baselines and a state-of-the-art video summarization model on this new benchmark.

In the real world, the class of a time series is usually labeled at the final time, but many applications require to classify time series at every time point. e.g. the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. Thus, we propose a new concept: Continuous Classification of Time Series (CCTS). It requires the model to learn data in different time stages. But the time series evolves dynamically, leading to different data distributions. When a model learns multi-distribution, it always forgets or overfits. We suggest that meaningful learning scheduling is potential due to an interesting observation: Measured by confidence, the process of model learning multiple distributions is similar to the process of human learning multiple knowledge. Thus, we propose a novel Confidence-guided method for CCTS (C3TS). It can imitate the alternating human confidence described by the Dunning-Kruger Effect. We define the objective- confidence to arrange data, and the self-confidence to control the learning duration. Experiments on four real-world datasets show that C3TS is more accurate than all baselines for CCTS.

Vision-language navigation (VLN), in which an agent follows language instruction in a visual environment, has been studied under the premise that the input command is fully feasible in the environment. Yet in practice, a request may not be possible due to language ambiguity or environment changes. To study VLN with unknown command feasibility, we introduce a new dataset Mobile app Tasks with Iterative Feedback (MoTIF), where the goal is to complete a natural language command in a mobile app. Mobile apps provide a scalable domain to study real downstream uses of VLN methods. Moreover, mobile app commands provide instruction for interactive navigation, as they result in action sequences with state changes via clicking, typing, or swiping. MoTIF is the first to include feasibility annotations, containing both binary feasibility labels and fine-grained labels for why tasks are unsatisfiable. We further collect follow-up questions for ambiguous queries to enable research on task uncertainty resolution. Equipped with our dataset, we propose the new problem of feasibility prediction, in which a natural language instruction and multimodal app environment are used to predict command feasibility. MoTIF provides a more realistic app dataset as it contains many diverse environments, high-level goals, and longer action sequences than prior work. We evaluate interactive VLN methods using MoTIF, quantify the generalization ability of current approaches to new app environments, and measure the effect of task feasibility on navigation performance.

Drori et al. (2022) report that "A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level ... [It] automatically answers 81\% of university-level mathematics problems." The system they describe is indeed impressive; however, the above description is very much overstated. The work of solving the problems is done, not by a neural network, but by the symbolic algebra package Sympy. Problems of various formats are excluded from consideration. The so-called "explanations" are just rewordings of lines of code. Answers are marked as correct that are not in the form specified in the problem. Most seriously, it seems that in many cases the system uses the correct answer given in the test corpus to guide its path to solving the problem.

"AI for Ukraine" is a series of workshops and lectures held by international artificial intelligence experts to support the development of Ukraine's tech community during the war. Montreal), Alex J. Smola (Amazon Web), Sebastian Bubeck (Microsoft), Gaël Varoquaux (INRIA), and many other well-known specialists have joined the initiative. This is a non-commercial educational project by AI HOUSE – a company focused on building the AI/ML community in Ukraine and is part of the Roosh tech ecosystem. All proceeds collected upon registration will be donated to the biggest Ukrainian charity fund "Come Back Alive". It's been five months of a completely new reality for every single Ukrainian, one with sirens, bombings, pain, and war.

On Saturday morning, June 11, Jeff Bezo's newspaper The Washington Post published a story under the headline "The Google engineer who thinks the company's AI has come to life." The headline was followed by a brief explanation of Blake Lamoine, a Southern grown, former U.S. military, ex-convict, Christian mystic, AI researcher, father, and genius of compassion (I added that last part) and his belief that there's "a ghost in the machine."* If your eyes haven't rolled to the back of your head yet, then chances are you're reading this from the front porch of a double-wide trailer parked somewhere below the Mason Dixon with a glass of sweet tea in your hand and a coon dog at your feet. Which is clearly not something any "reasonable" person would choose to do in the year 2022. Or if, like me, you're a bit more progressed from the stereotype, you might be standing in front of a classroom of semi-attentive undergraduate students at a Southeastern research university making your best effort to bridge the ever-widening practical and theoretical gaps between old-world journalistic traditions and new-age neoliberal ideologies related to the function of human language in society.

Data Science and Machine Learning Service will help the customer to also get overview about the global markets and establishing their business at the …