Given the enormous number of instructional videos available online, learning a diverse array of multi-step task models from videos is an appealing goal. We introduce a new pre-trained video model, VideoTaskformer, focused on representing the semantics and structure of instructional videos. We pre-train VideoTaskformer using a simple and effective objective: predicting weakly supervised textual labels for steps that are randomly masked out from an instructional video (masked step modeling). Compared to prior work which learns step representations locally, our approach involves learning them globally, leveraging video of the entire surrounding task as context. From these learned representations, we can verify if an unseen video correctly executes a given task, as well as forecast which steps are likely to be taken after a given step. We introduce two new benchmarks for detecting mistakes in instructional videos, to verify if there is an anomalous step and if steps are executed in the right order. We also introduce a long-term forecasting benchmark, where the goal is to predict long-range future steps from a given step. Our method outperforms previous baselines on these tasks, and we believe the tasks will be a valuable way for the community to measure the quality of step representations. Additionally, we evaluate VideoTaskformer on 3 existing benchmarks -- procedural activity recognition, step classification, and step forecasting -- and demonstrate on each that our method outperforms existing baselines and achieves new state-of-the-art performance.

Learn the basics of reinforcement learning and how to implement it using Gymnasium (previously called OpenAI Gym). Gymnasium is an open source Python library originally created by OpenAI that provides a collection of pre-built environments for reinforcement learning agents. It provides a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. Reinforcement learning is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward.

The training and running of an online Go system require the support of effective data management systems to deal with vast data, such as the initial Go game records, the feature data set obtained by representation learning, the experience data set of self-play, the randomly sampled Monte Carlo tree, and so on. Previous work has rarely mentioned this problem, but the ability and efficiency of data management systems determine the accuracy and speed of the Go system. To tackle this issue, we propose an online Go game system based on the chunk data storage method (CH-Go), which processes the format of 160k Go game data released by Kiseido Go Server (KGS) and designs a Go encoder with 11 planes, a parallel processor and generator for better memory performance. Specifically, we store the data in chunks, take the chunk size of 1024 as a batch, and save the features and labels of each chunk as binary files. Then a small set of data is randomly sampled each time for the neural network training, which is accessed by batch through yield method. The training part of the prototype includes three modules: supervised learning module, reinforcement learning module, and an online module. Firstly, we apply Zobrist-guided hash coding to speed up the Go board construction. Then we train a supervised learning policy network to initialize the self-play for generation of experience data with 160k Go game data released by KGS. Finally, we conduct reinforcement learning based on REINFORCE algorithm. Experiments show that the training accuracy of CH- Go in the sampled 150 games is 99.14%, and the accuracy in the test set is as high as 98.82%. Under the condition of limited local computing power and time, we have achieved a better level of intelligence. Given the current situation that classical systems such as GOLAXY are not free and open, CH-Go has realized and maintained complete Internet openness.

If you have been using twitter recently I bet that from the last 10 tweets 5 of them are linked to AI and the rise of chatGPT. Looking at those tweets AI tools are going to change the world as we know it. This is even more significant in the case of Education and in particular in Higher Education where most of the traditional methods of assessments are based on essay that consists on pieces of written work where students have to answer questions in a specific number of words. A lot of messages that I hear from institutions, and normally from traditional institutions, is that we need to ban chatGPT as this is a danger and a temptation to student to cheat and create this contractual cheating situation were students are submitting work that is not they original work. I think that this view is completely wrong and it is just a way to avoid the problem without thinking first why there is a problem and second what is actually AI and the possible benefits that can bring to education, learning outcomes and yes to assessments.

Ready to build the future with Deep Neural Networks? Stand on the shoulder of TensorFlow and Keras for Machine Learning.

Microsoft shares rose 12.4% last week on word of the release of Copilot, a generative artificial intelligence tool to be integrated into its Office suite. That's huge news from the tech giant because it hands AI to the masses via highly familiar, everyday interfaces such as Word, Excel, PowerPoint and Outlook. Copilot will swiftly bring significant efficiencies and improvements to common tasks including email, analyses, business cases, presentations and performance reviews. With streamlined workflows and automated administrative functions, companies will be challenged to rethink business models, talent needs and resource usage. Very quickly, it will spur creativity, shorten work timelines and improve results.

In this paper, we present a demo of an intelligent personal agent called Hey Dona (or just Dona) with virtual voice assistance in student course registration. It is a deployed project in the theme of AI for education. In this digital age with a myriad of smart devices, users often delegate tasks to agents. While pointing and clicking supersedes the erstwhile command-typing, modern devices allow users to speak commands for agents to execute tasks, enhancing speed and convenience. In line with this progress, Dona is an intelligent agent catering to student needs by automated, voice-operated course registration, spanning a multitude of accents, entailing task planning optimization, with some language translation as needed. Dona accepts voice input by microphone (Bluetooth, wired microphone), converts human voice to computer understandable language, performs query processing as per user commands, connects with the Web to search for answers, models task dependencies, imbibes quality control, and conveys output by speaking to users as well as displaying text, thus enabling human-AI interaction by speech cum text. It is meant to work seamlessly on desktops, smartphones etc. and in indoor as well as outdoor settings. To the best of our knowledge, Dona is among the first of its kind as an intelligent personal agent for voice assistance in student course registration. Due to its ubiquitous access for educational needs, Dona directly impacts AI for education. It makes a broader impact on smart city characteristics of smart living and smart people due to its contributions to providing benefits for new ways of living and assisting 21st century education, respectively.

Simultaneous machine translation, which aims at a real-time translation, is useful in many live scenarios but very challenging due to the trade-off between accuracy and latency. To achieve the balance for both, the model needs to wait for appropriate streaming text (READ policy) and then generates its translation (WRITE policy). However, WRITE policies of previous work either are specific to the method itself due to the end-to-end training or suffer from the input mismatch between training and decoding for the non-end-to-end training. Therefore, it is essential to learn a generic and better WRITE policy for simultaneous machine translation. Inspired by strategies utilized by human interpreters and "wait" policies, we propose a novel adaptive prefix-to-prefix training policy called LEAPT, which allows our machine translation model to learn how to translate source sentence prefixes and make use of the future context. Experiments show that our proposed methods greatly outperform competitive baselines and achieve promising results.

TensorFlow is by far, the most popular library for deep learning. Backed by Google, it is a solid investment of your time and efforts if you want to succeed in the area of machine learning and AI. The issue most people face is that getting started with Tensorflow guides usually delve too deeply into unnecessary mathematics. That is where this course comes in. While some theory is important, a lot of it is just not needed when you're just getting started!

Drexel University has recently launched a new Artificial Intelligence and Machine Learning (AI/ML) learning group. This initiative is designed to help students, faculty, and staff gain the skills necessary to develop AI/ML applications for research and industry. The goal of this program is to create an environment where people can come together to learn about the latest advancements in AI/ML technology while also gaining hands-on experience with real-world projects. The Drexel AI/ML learning group will be led by Dr. Yaser Abu-Mostafa, Professor of Electrical Engineering at Caltech, who brings decades of experience in machine learning research and teaching. He will be joined by other experts from academia as well as industry professionals who have expertise in various aspects of artificial intelligence and machine learning development.