This paper contributes a novel learning-based method for aggressive task-driven compression of depth images and their encoding as images tailored to collision prediction for robotic systems. A novel 3D image processing methodology is proposed that accounts for the robot's size in order to appropriately "inflate" the obstacles represented in the depth image and thus obtain the distance that can be traversed by the robot in a collision-free manner along any given ray within the camera frustum. Such depth-and-collision image pairs are used to train a neural network that follows the architecture of Variational Autoencoders to compress-and-transform the information in the original depth image to derive a latent representation that encodes the collision information for the given depth image. We compare our proposed task-driven encoding method with classical task-agnostic methods and demonstrate superior performance for the task of collision image prediction from extremely low-dimensional latent spaces. A set of comparative studies show that the proposed approach is capable of encoding depth image-and-collision image tuples from complex scenes with thin obstacles at long distances better than the classical methods at compression ratios as high as 4050:1.
相關內容
This paper proposes a method to estimate the class separability of an unlabeled text dataset by inspecting the topological characteristics of sentence-transformer embeddings of the text. Experiments conducted involve both binary and multi-class cases, with balanced and imbalanced scenarios. The results demonstrate a clear correlation and a better consistency between the proposed method and other separability and classification metrics, such as Thornton's method and the AUC score of a logistic regression classifier, as well as unsupervised methods. Finally, we empirically show that the proposed method can be part of a stopping criterion for fine-tuning language-model classifiers. By monitoring the class separability of the embedding space after each training iteration, we can detect when the training process stops improving the separability of the embeddings without using additional labels.
This work presents a camera model for refractive media such as water and its application in underwater visual-inertial odometry. The model is self-calibrating in real-time and is free of known correspondences or calibration targets. It is separable as a distortion model (dependent on refractive index $n$ and radial pixel coordinate) and a virtual pinhole model (as a function of $n$). We derive the self-calibration formulation leveraging epipolar constraints to estimate the refractive index and subsequently correct for distortion. Through experimental studies using an underwater robot integrating cameras and inertial sensing, the model is validated regarding the accurate estimation of the refractive index and its benefits for robust odometry estimation in an extended envelope of conditions. Lastly, we show the transition between media and the estimation of the varying refractive index online, thus allowing computer vision tasks across refractive media.
This paper shows a novel machine learning model for realized volatility (RV) prediction using a normalizing flow, an invertible neural network. Since RV is known to be skewed and have a fat tail, previous methods transform RV into values that follow a latent distribution with an explicit shape and then apply a prediction model. However, knowing that shape is non-trivial, and the transformation result influences the prediction model. This paper proposes to jointly train the transformation and the prediction model. The training process follows a maximum-likelihood objective function that is derived from the assumption that the prediction residuals on the transformed RV time series are homogeneously Gaussian. The objective function is further approximated using an expectation-maximum algorithm. On a dataset of 100 stocks, our method significantly outperforms other methods using analytical or naive neural-network transformations.
This paper proposes a new method for differentiating through optimal trajectories arising from non-convex, constrained discrete-time optimal control (COC) problems using the implicit function theorem (IFT). Previous works solve a differential Karush-Kuhn-Tucker (KKT) system for the trajectory derivative, and achieve this efficiently by solving an auxiliary Linear Quadratic Regulator (LQR) problem. In contrast, we directly evaluate the matrix equations which arise from applying variable elimination on the Lagrange multiplier terms in the (differential) KKT system. By appropriately accounting for the structure of the terms within the resulting equations, we show that the trajectory derivatives scale linearly with the number of timesteps. Furthermore, our approach allows for easy parallelization, significantly improved scalability with model size, direct computation of vector-Jacobian products and improved numerical stability compared to prior works. As an additional contribution, we unify prior works, addressing claims that computing trajectory derivatives using IFT scales quadratically with the number of timesteps. We evaluate our method on a both synthetic benchmark and four challenging, learning from demonstration benchmarks including a 6-DoF maneuvering quadrotor and 6-DoF rocket powered landing.
This paper introduces a novel adaptive transmission scheme to amplify the prowess of coordinated direct and relay transmission (CDRT) systems rooted in non-orthogonal multiple access principles. Leveraging the maximum ratio transmission scheme, we seamlessly meet the prerequisites of CDRT while harnessing the potential of dynamic power allocation and directional antennas to elevate the system's operational efficiency. Through meticulous derivations, we unveil closed-form expressions depicting the exact effective sum throughput. Our simulation results adeptly validate the theoretical analysis and vividly showcase the effectiveness of the proposed scheme.
This paper considers the use of machine learning algorithms for predicting cocaine use based on magnetic resonance imaging (MRI) connectomic data. The study utilized functional MRI (fMRI) and diffusion MRI (dMRI) data collected from 275 individuals, which was then parcellated into 246 regions of interest (ROIs) using the Brainnetome atlas. After data preprocessing, the datasets were transformed into tensor form. We developed a tensor-based unsupervised machine learning algorithm to reduce the size of the data tensor from $275$ (individuals) $\times 2$ (fMRI and dMRI) $\times 246$ (ROIs) $\times 246$ (ROIs) to $275$ (individuals) $\times 2$ (fMRI and dMRI) $\times 6$ (clusters) $\times 6$ (clusters). This was achieved by applying the high-order Lloyd algorithm to group the ROI data into 6 clusters. Features were extracted from the reduced tensor and combined with demographic features (age, gender, race, and HIV status). The resulting dataset was used to train a Catboost model using subsampling and nested cross-validation techniques, which achieved a prediction accuracy of 0.857 for identifying cocaine users. The model was also compared with other models, and the feature importance of the model was presented. Overall, this study highlights the potential for using tensor-based machine learning algorithms to predict cocaine use based on MRI connectomic data and presents a promising approach for identifying individuals at risk of substance abuse.
This paper addresses the problem of generating questions from a given context and an answer, specifically focusing on questions that require multi-hop reasoning across an extended context. Previous studies have suggested that key phrase selection is essential for question generation (QG), yet it is still challenging to connect such disjointed phrases into meaningful questions, particularly for long context. To mitigate this issue, we propose MultiFactor, a novel QG framework based on multi-level content planning. Specifically, MultiFactor includes two components: FA-model, which simultaneously selects key phrases and generates full answers, and Q-model which takes the generated full answer as an additional input to generate questions. Here, full answer generation is introduced to connect the short answer with the selected key phrases, thus forming an answer-aware summary to facilitate QG. Both FA-model and Q-model are formalized as simple-yet-effective Phrase-Enhanced Transformers, our joint model for phrase selection and text generation. Experimental results show that our method outperforms strong baselines on two popular QG datasets. Our code is available at //github.com/zeaver/MultiFactor.
This paper provides norm-based generalization bounds for the Transformer architecture that do not depend on the input sequence length. We employ a covering number based approach to prove our bounds. We use three novel covering number bounds for the function class of bounded linear transformations to upper bound the Rademacher complexity of the Transformer. Furthermore, we show this generalization bound applies to the common Transformer training technique of masking and then predicting the masked word. We also run a simulated study on a sparse majority data set that empirically validates our theoretical findings.
This paper presents a novel approach to enhance the performance of binary code comment quality classification models through the application of Generative Artificial Intelligence (AI). By leveraging the OpenAI API, a dataset comprising 1239 newly generated code-comment pairs, extracted from various GitHub repositories and open-source projects, has been labelled as "Useful" or "Not Useful", and integrated into the existing corpus of 9048 pairs in the C programming language. Employing a cutting-edge Large Language Model Architecture, the generated dataset demonstrates notable improvements in model accuracy. Specifically, when incorporated into the Support Vector Machine (SVM) model, a 6% increase in precision is observed, rising from 0.79 to 0.85. Additionally, the Artificial Neural Network (ANN) model exhibits a 1.5% increase in recall, climbing from 0.731 to 0.746. This paper sheds light on the potential of Generative AI in augmenting code comment quality classification models. The results affirm the effectiveness of this methodology, indicating its applicability in broader contexts within software development and quality assurance domains. The findings underscore the significance of integrating generative techniques to advance the accuracy and efficacy of machine learning models in practical software engineering scenarios.
This paper explores meta-learning in sequential recommendation to alleviate the item cold-start problem. Sequential recommendation aims to capture user's dynamic preferences based on historical behavior sequences and acts as a key component of most online recommendation scenarios. However, most previous methods have trouble recommending cold-start items, which are prevalent in those scenarios. As there is generally no side information in the setting of sequential recommendation task, previous cold-start methods could not be applied when only user-item interactions are available. Thus, we propose a Meta-learning-based Cold-Start Sequential Recommendation Framework, namely Mecos, to mitigate the item cold-start problem in sequential recommendation. This task is non-trivial as it targets at an important problem in a novel and challenging context. Mecos effectively extracts user preference from limited interactions and learns to match the target cold-start item with the potential user. Besides, our framework can be painlessly integrated with neural network-based models. Extensive experiments conducted on three real-world datasets verify the superiority of Mecos, with the average improvement up to 99%, 91%, and 70% in HR@10 over state-of-the-art baseline methods.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191