In this paper, we investigate the convergence properties of the stochastic gradient descent (SGD) method and its variants, especially in training neural networks built from nonsmooth activation functions. We develop a novel framework that assigns different timescales to stepsizes for updating the momentum terms and variables, respectively. Under mild conditions, we prove the global convergence of our proposed framework in both single-timescale and two-timescale cases. We show that our proposed framework encompasses a wide range of well-known SGD-type methods, including heavy-ball SGD, SignSGD, Lion, normalized SGD and clipped SGD. Furthermore, when the objective function adopts a finite-sum formulation, we prove the convergence properties for these SGD-type methods based on our proposed framework. In particular, we prove that these SGD-type methods find the Clarke stationary points of the objective function with randomly chosen stepsizes and initial points under mild assumptions. Preliminary numerical experiments demonstrate the high efficiency of our analyzed SGD-type methods.

The dawn of artificial intelligence tools like ChatGPT may revolutionize the way both the public and private sector use data to ferret out risks and opportunities in the $32 trillion global trading system. During the pandemic, government agencies and industries like financial services and telecommunications accelerated their adoption of machine-learning tools. But many involved in trade were caught in analog, paper-laden transactions playing catch-up. Now, after three years of historic trade disruptions, generative AI and language-learning models have emerged just when governments and companies need them to better manage the world's convoluted supply lines.

We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA -- an extension of NExT-QA with 10.5$K$ temporal grounding (or location) labels tied to the original QA pairs. With NExT-GQA, we scrutinize a variety of state-of-the-art VLMs. Through post-hoc attention analysis, we find that these models are weak in substantiating the answers despite their strong QA performance. This exposes a severe limitation of these models in making reliable predictions. As a remedy, we further explore and suggest a video grounding mechanism via Gaussian mask optimization and cross-modal learning. Experiments with different backbones demonstrate that this grounding mechanism improves both video grounding and QA. Our dataset and code are released. With these efforts, we aim to push towards the reliability of deploying VLMs in VQA systems.

Multimodal signals, including text, audio, image and video, can be integrated into Semantic Communication (SC) for providing an immersive experience with low latency and high quality at the semantic level. However, the multimodal SC has several challenges, including data heterogeneity, semantic ambiguity, and signal fading. Recent advancements in large AI models, particularly in Multimodal Language Model (MLM) and Large Language Model (LLM), offer potential solutions for these issues. To this end, we propose a Large AI Model-based Multimodal SC (LAM-MSC) framework, in which we first present the MLM-based Multimodal Alignment (MMA) that utilizes the MLM to enable the transformation between multimodal and unimodal data while preserving semantic consistency. Then, a personalized LLM-based Knowledge Base (LKB) is proposed, which allows users to perform personalized semantic extraction or recovery through the LLM. This effectively addresses the semantic ambiguity. Finally, we apply the Conditional Generative adversarial networks-based channel Estimation (CGE) to obtain Channel State Information (CSI). This approach effectively mitigates the impact of fading channels in SC. Finally, we conduct simulations that demonstrate the superior performance of the LAM-MSC framework.

The Knowledge Tracing (KT) task plays a crucial role in personalized learning, and its purpose is to predict student responses based on their historical practice behavior sequence. However, the KT task suffers from data sparsity, which makes it challenging to learn robust representations for students with few practice records and increases the risk of model overfitting. Therefore, in this paper, we propose a Cognition-Mode Aware Variational Representation Learning Framework (CMVF) that can be directly applied to existing KT methods. Our framework uses a probabilistic model to generate a distribution for each student, accounting for uncertainty in those with limited practice records, and estimate the student's distribution via variational inference (VI). In addition, we also introduce a cognition-mode aware multinomial distribution as prior knowledge that constrains the posterior student distributions learning, so as to ensure that students with similar cognition modes have similar distributions, avoiding overwhelming personalization for students with few practice records. At last, extensive experimental results confirm that CMVF can effectively aid existing KT methods in learning more robust student representations. Our code is available at https://github.com/zmy-9/CMVF.

In federated learning (FL), clients with limited resources can disrupt the training efficiency. A potential solution to this problem is to leverage a new learning procedure that does not rely on backpropagation (BP). We present a novel approach to FL called FedFwd that employs a recent BP-free method by Hinton (2022), namely the Forward Forward algorithm, in the local training process. FedFwd can reduce a significant amount of computations for updating parameters by performing layer-wise local updates, and therefore, there is no need to store all intermediate activation values during training. We conduct various experiments to evaluate FedFwd on standard datasets including MNIST and CIFAR-10, and show that it works competitively to other BP-dependent FL methods.

They say you should learn something new every day. Well, with The Unlimited Lifetime Learning Subscription Bundle, you actually can, and it's specially discounted during our Labor Day sale. This bundle includes lifetime subscriptions to Rosetta Stone and StackSkills Unlimited. Yes, that Rosetta Stone that has been trusted by international organizations like NASA and TripAdvisor for three decades and is considered the gold standard for language learning by CNN. StackSkills Unlimited, for its part, gives you access to more than 1,000 online courses on-demand from more than 350 of the web's top instructors.

Rick Clark, executive director of undergraduate admission at the Georgia Institute of Technology, and his staff spent weeks this summer pretending to be high school students using artificial intelligence chatbots to fill out college applications. The admissions officers each took on a different high school persona: swim team captain, Eagle Scout, musical theater performer. Then they fed personal details about the fictional students into ChatGPT, prompting the AI chatbot to produce the kind of extracurricular activity lists and personal essays commonly required on college applications. Clark said he wanted to get a handle on how AI chatbots might reshape the admissions process this fall -- the start of the first full academic year that the tools will be widely available to high school seniors -- and come up with guidance for students applying to Georgia Tech.

Deep learning has been widely used recently for sound event detection and classification. Its success is linked to the availability of sufficiently large datasets, possibly with corresponding annotations when supervised learning is considered. In bioacoustic applications, most tasks come with few labelled training data, because annotating long recordings is time consuming and costly. Therefore supervised learning is not the best suited approach to solve bioacoustic tasks. The bioacoustic community recasted the problem of sound event detection within the framework of few-shot learning, i.e. training a system with only few labeled examples. The few-shot bioacoustic sound event detection task in the DCASE challenge focuses on detecting events in long audio recordings given only five annotated examples for each class of interest. In this paper, we show that learning a rich feature extractor from scratch can be achieved by leveraging data augmentation using a supervised contrastive learning framework. We highlight the ability of this framework to transfer well for five-shot event detection on previously unseen classes in the training data. We obtain an F-score of 63.46\% on the validation set and 42.7\% on the test set, ranking second in the DCASE challenge. We provide an ablation study for the critical choices of data augmentation techniques as well as for the learning strategy applied on the training set.

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neurosymbolic Reinforcement Learning (Neurosymbolic RL). Compared to traditional learning methods, Neurosymbolic AI offers significant advantages by simplifying complexity and providing transparency and explainability. Reinforcement Learning(RL), a long-standing Artificial Intelligence(AI) concept that mimics human behavior using rewards and punishment, is a fundamental component of Neurosymbolic RL, a recent integration of the two fields that has yielded promising results. The aim of this paper is to contribute to the emerging field of Neurosymbolic RL by conducting a literature survey. Our evaluation focuses on the three components that constitute Neurosymbolic RL: neural, symbolic, and RL. We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies:Learning for Reasoning, Reasoning for Learning and Learning-Reasoning. These categories are further divided into sub-categories based on their applications. Furthermore, we analyze the RL components of each research work, including the state space, action space, policy module, and RL algorithm. Additionally, we identify research opportunities and challenges in various applications within this dynamic field.