This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes. Shoggoth uses online knowledge distillation to improve the accuracy of models suffering from data drift and offloads the labeling process to the cloud, alleviating constrained resources of edge devices. At the edge, we design adaptive training using small batches to adapt models under limited computing power, and adaptive sampling of training frames for robustness and reducing bandwidth. The evaluations on the realistic dataset show 15%-20% model accuracy improvement compared to the edge-only strategy and fewer network costs than the cloud-only strategy.

In the field of machine reading comprehension (MRC), existing systems have surpassed the average performance of human beings in many tasks like SQuAD. However, there is still a long way to go when it comes to logical reasoning. Although some methods for it have been put forward, they either are designed in a quite complicated way or rely too much on external structures. In this paper, we proposed IDOL (InDicator-Oriented Logic Pre-training), an easy-to-understand but highly effective further pre-training task which logically strengthens the pre-trained models with the help of 6 types of logical indicators and a logically rich dataset LGP (LoGic Pre-training). IDOL achieves state-of-the-art performance on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC, and is proven to be capable of generalizing to different pre-trained models and other types of MRC benchmarks like RACE and SQuAD 2.0 while keeping competitive general language understanding ability through testing on tasks in GLUE. Besides, at the beginning of the era of large language models, we take several of them like ChatGPT into comparison and find that IDOL still shows its advantage.

The forward-forward algorithm [Hinton, 2022] presents a new method of training neural networks by updating weights during an inference, performing parameter updates for each layer individually. This immediately reduces memory requirements during training and may lead to many more benefits, like seamless online training. This method relies on a loss ("goodness") function that can be evaluated on the activations of each layer, of which can have a varied parameter size, depending on the hyperparamaterization of the network. In the seminal paper, a goodness function was proposed to fill this need; however, if placed in a one-class problem context, one need not pioneer a new loss because these functions can innately handle dynamic network sizes. In this paper, we investigate the performance of deep one-class objective functions when trained in a forward-forward fashion.

Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adversarial Distillation (FAD) method, a generic adversarial loss function in point cloud distillation, to reduce loss during knowledge transfer. In the feature extraction stage, the features extracted by the teacher are used as the discriminator, and the students continuously generate new features in the training stage. The feature of the student is obtained by attacking the feedback from the teacher and getting a score to judge whether the student has learned the knowledge well or not. In experiments on standard point cloud classification on ModelNet40 and ScanObjectNN datasets, our method reduced the information loss of knowledge transfer in distillation in 40x model compression while maintaining competitive performance.

Multi-view clustering has attracted broad attention due to its capacity to utilize consistent and complementary information among views. Although tremendous progress has been made recently, most existing methods undergo high complexity, preventing them from being applied to large-scale tasks. Multi-view clustering via matrix factorization is a representative to address this issue. However, most of them map the data matrices into a fixed dimension, limiting the model's expressiveness. Moreover, a range of methods suffers from a two-step process, i.e., multimodal learning and the subsequent $k$-means, inevitably causing a sub-optimal clustering result. In light of this, we propose a one-step multi-view clustering with diverse representation method, which incorporates multi-view learning and $k$-means into a unified framework. Specifically, we first project original data matrices into various latent spaces to attain comprehensive information and auto-weight them in a self-supervised manner. Then we directly use the information matrices under diverse dimensions to obtain consensus discrete clustering labels. The unified work of representation learning and clustering boosts the quality of the final results. Furthermore, we develop an efficient optimization algorithm with proven convergence to solve the resultant problem. Comprehensive experiments on various datasets demonstrate the promising clustering performance of our proposed method.

Suppose we are given access to $n$ independent samples from distribution $\mu$ and we wish to output one of them with the goal of making the output distributed as close as possible to a target distribution $\nu$. In this work we show that the optimal total variation distance as a function of $n$ is given by $\tilde\Theta(\frac{D}{f'(n)})$ over the class of all pairs $\nu,\mu$ with a bounded $f$-divergence $D_f(\nu\|\mu)\leq D$. Previously, this question was studied only for the case when the Radon-Nikodym derivative of $\nu$ with respect to $\mu$ is uniformly bounded. We then consider an application in the seemingly very different field of smoothed online learning, where we show that recent results on the minimax regret and the regret of oracle-efficient algorithms still hold even under relaxed constraints on the adversary (to have bounded $f$-divergence, as opposed to bounded Radon-Nikodym derivative). Finally, we also study efficacy of importance sampling for mean estimates uniform over a function class and compare importance sampling with rejection sampling.

Lifelong learning has recently attracted attention in building machine learning systems that continually accumulate and transfer knowledge to help future learning. Unsupervised topic modeling has been popularly used to discover topics from document collections. However, the application of topic modeling is challenging due to data sparsity, e.g., in a small collection of (short) documents and thus, generate incoherent topics and sub-optimal document representations. To address the problem, we propose a lifelong learning framework for neural topic modeling that can continuously process streams of document collections, accumulate topics and guide future topic modeling tasks by knowledge transfer from several sources to better deal with the sparse data. In the lifelong process, we particularly investigate jointly: (1) sharing generative homologies (latent topics) over lifetime to transfer prior knowledge, and (2) minimizing catastrophic forgetting to retain the past learning via novel selective data augmentation, co-training and topic regularization approaches. Given a stream of document collections, we apply the proposed Lifelong Neural Topic Modeling (LNTM) framework in modeling three sparse document collections as future tasks and demonstrate improved performance quantified by perplexity, topic coherence and information retrieval task.

As more doctors and nurses leave the profession, providers are turning to AI technology to help bridge the coverage gap, especially among older Americans. More than one out of four older people experience a fall each year -- and three million of them are treated in the emergency room for their injuries, according to statistics from the Centers for Disease Control and Prevention (CDC). Dangerous falls can be prevented by following safety protocols. Christynne Helfrich, PT, a physical therapist commercial consultant for Hinge Health in Illinois, shared some expert tips with Fox News Digital. Going for daily walks or engaging in other low-impact physical activities can help to strengthen muscles, keep joints flexible and maintain overall endurance, Helfrich said.

A decade after its widespread adoption, it's safe to say that U.S. schools utterly failed to acclimate our students to social media and to anticipate the profound damage it could do. The result of widespread social media use among students (said the U.S. surgeon general in a recent advisory) is increased anxiety, stress, and depression. As a school technology specialist working with a population of middle- and high-schoolers, I see firsthand parents' desperation when I host standing-room-only sessions about social media and mental health. With the swift emergence of A.I., educators have an opportunity to do better. This summer, K–12 schools must get to work drafting academic policies governing the use of A.I. and facilitating professional development for teachers about the new technology.

Scientists have developed hundreds of techniques to measure the interactions between pairs of processes in complex systems. But these computational methods, from correlation coefficients to causal inference, rely on distinct quantitative theories that remain largely disconnected. Here we introduce a library of 237 statistics of pairwise interactions and assess their behavior on 1053 multivariate time series from a wide range of real-world and model-generated systems. Our analysis highlights new commonalities between different mathematical formulations, providing a unified picture of a rich interdisciplinary literature. Using three real-world case studies, we then show that simultaneously leveraging diverse methods from across science can uncover those most suitable for addressing a given problem, yielding interpretable understanding of the conceptual formulations of pairwise dependence that drive successful performance. Our framework is provided in extendable open software, enabling comprehensive data-driven analysis by integrating decades of methodological advances.