Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the [class] token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, i.e., accelerating large-scale vision transformers for dense prediction without any additional re-training or finetuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a token clustering layer to decrease the number of tokens and a token reconstruction layer to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation. Accordingly, our method accelerates 40% FPS and saves 30% GFLOPs of "Segmenter+ViT-L/16" while maintaining 99.5% of the performance on ADE20K without fine-tuning the official weights.

Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically thought to underlie learning in the brain, the precise neural and synaptic mechanisms by which learning processes improve through experience are not well understood. Here, we present a general-purpose, biologically-plausible meta-learning rule which estimates gradients with respect to the parameters of an underlying learning algorithm by simply running it twice. Our rule may be understood as a generalization of contrastive Hebbian learning to meta-learning and notably, it neither requires computing second derivatives nor going backwards in time, two characteristic features of previous gradient-based methods that are hard to conceive in physical neural circuits. We demonstrate the generality of our rule by applying it to two distinct models: a complex synapse with internal states which consolidate task-shared information, and a dual-system architecture in which a primary network is rapidly modulated by another one to learn the specifics of each task. For both models, our meta-learning rule matches or outperforms reference algorithms on a wide range of benchmark problems, while only using information presumed to be locally available at neurons and synapses. We corroborate these findings with a theoretical analysis of the gradient estimation error incurred by our rule.

Data is the fuel powering AI and creates tremendous value for many domains. However, collecting datasets for AI is a time-consuming, expensive, and complicated endeavor. For practitioners, data investment remains to be a leap of faith in practice. In this work, we study the data budgeting problem and formulate it as two sub-problems: predicting (1) what is the saturating performance if given enough data, and (2) how many data points are needed to reach near the saturating performance. Different from traditional dataset-independent methods like PowerLaw, we proposed a learning method to solve data budgeting problems. To support and systematically evaluate the learning-based method for data budgeting, we curate a large collection of 383 tabular ML datasets, along with their data vs performance curves. Our empirical evaluation shows that it is possible to perform data budgeting given a small pilot study dataset with as few as $50$ data points.

Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference trade-off problem between different examples. However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available. In this work, we propose a novel efficient meta-learning algorithm for solving the online continual learning problem, where the regularization terms and learning rates are adapted to the Taylor approximation of the parameter's importance to mitigate forgetting. The proposed method expresses the gradient of the meta-loss in closed-form and thus avoid computing second-order derivative which is computationally inhibitable. We also use Proximal Gradient Descent to further improve computational efficiency and accuracy. Experiments on diverse benchmarks show that our method achieves better or on-par performance and much higher efficiency compared to the state-of-the-art approaches.

We present a novel differentiable weighted generalized iterative closest point (WGICP) method applicable to general 3D point cloud data, including that from Lidar. Our method builds on differentiable generalized ICP (GICP), and we propose using the differentiable K-Nearest Neighbor (KNN) algorithm to enhance differentiability. The differentiable GICP algorithm provides the gradient of output pose estimation with respect to each input point, which allows us to train a neural network to predict its importance, or weight, in estimating the correct pose. In contrast to the other ICP-based methods that use voxel-based downsampling or matching methods to reduce the computational cost, our method directly reduces the number of points used for GICP by only selecting those with the highest weights and ignoring redundant ones with lower weights. We show that our method improves both accuracy and speed of the GICP algorithm for the KITTI dataset and can be used to develop a more robust and efficient SLAM system.

Background and Objective: Parkinson's disease (PD) is the second most common progressive neurological condition after Alzheimer's, characterized by motor and non-motor symptoms. Developing a method to diagnose the condition in its beginning phases is essential because of the significant number of individuals afflicting with this illness. PD is typically identified using motor symptoms or other Neuroimaging techniques, such as DATSCAN and SPECT. These methods are expensive, time-consuming, and unavailable to the general public; furthermore, they are not very accurate. These constraints encouraged us to develop a novel technique using SHAP and Hard Voting Ensemble Method based on voice signals. Methods: In this article, we used Pearson Correlation Coefficients to understand the relationship between input features and the output, and finally, input features with high correlation were selected. These selected features were classified by the Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Gradient Boosting, and Bagging. Moreover, the Hard Voting Ensemble Method was determined based on the performance of the four classifiers. At the final stage, we proposed Shapley Additive exPlanations (SHAP) to rank the features according to their significance in diagnosing Parkinson's disease. Results and Conclusion: The proposed method achieved 85.42% accuracy, 84.94% F1-score, 86.77% precision, 87.62% specificity, and 83.20% sensitivity. The study's findings demonstrated that the proposed method outperformed state-of-the-art approaches and can assist physicians in diagnosing Parkinson's cases.

My last note shared a few ways to make gradient descent more efficient so that ML models can learn faster, how to check if gradient descent is working, and how the normal equation can sometimes be a good shortcut for training models. This note will focus in on just one new key idea: the Sigmoid function. The Sigmoid function (also known as the logistic function) is a function that outputs a value between 0 and 1 depending on its input. It's value to machine learning models comes from being able to take a set of inputs (parameters θ multiplied by their respective features x) and translate them into a number between 0 and 1, especially as a probability. Here, it's also good to know that the sigmoid function is often used as the function within the nodes of a neural network.

The main objective of this work is to use machine-learning (ML) algorithms to develop a powerful model to predict well-integrity (WI) risk categories of gas-lifted wells. The model described in the complete paper can predict well-risk level and provide a unique method to convert associated failure risk of each element in the well envelope into tangible values. The predictive model, which predicts the risk status of wells and classifies their integrity level into five categories rather than three broad-range categories, as in qualitative risk classification. The five categories are Category 1, which is too risky Category 2, which is still too risky but less so than Category 1 Category 3, which is medium risk but can be elevated if additional barrier failures occur Category 4, which is low risk but features some impaired barriers Category 5, which is the lowest in risk The failure model, which identifies whether the well is considered to be in failure mode. In addition, the model can identify wells that require prompt mitigation.

This article was made in collaboration with Sean Eugene Chua, an undergraduate student at the University of Toronto who has shared experiences across fields that include data science, programming, and machine learning. By definition, it is when a machine can imitate human behavior and emulate how they think and act. A published paper written by logician Walter Pitts and neuroscientist Warren S. McCulloch entitled "A logical calculus of the ideas immanent in nervous activity" was regarded as a breakthrough in laying the first foundations of machine learning. It indicates the usage of mathematical principles to detail the science and psychology behind human decision-making. However, in 1950, Alan Turing introduced what computer scientists now know of as the "Turing Test" to determine whether a machine can be considered intelligent or unintelligent.

High quality energy systems information is a crucial input to energy systems research, modeling, and decision-making. Unfortunately, actionable information about energy systems is often of limited availability, incomplete, or only accessible for a substantial fee or through a non-disclosure agreement. Recently, remotely sensed data (e.g., satellite imagery, aerial photography) have emerged as a potentially rich source of energy systems information. However, the use of these data is frequently challenged by its sheer volume and complexity, precluding manual analysis. Recent breakthroughs in machine learning have enabled automated and rapid extraction of useful information from remotely sensed data, facilitating large-scale acquisition of critical energy system variables. Here we present a systematic review of the literature on this emerging topic, providing an in-depth survey and review of papers published within the past two decades. We first taxonomize the existing literature into ten major areas, spanning the energy value chain. Within each research area, we distill and critically discuss major features that are relevant to energy researchers, including, for example, key challenges regarding the accessibility and reliability of the methods. We then synthesize our findings to identify limitations and trends in the literature as a whole, and discuss opportunities for innovation. These include the opportunity to extend the methods beyond electricity to broader energy systems and wider geographic areas; and the ability to expand the use of these methods in research and decision making as satellite data become cheaper and easier to access. We also find that there are persistent challenges: limited standardization and rigor of performance assessments; limited sharing of code, which would improve replicability; and a limited consideration of the ethics and privacy of data.