Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to nonfederal websites. Their policies may differ from this site.

With funding from a National Science Foundation (NSF) IUSE/PFE: Revolutionizing Engineering and Computer Science Departments (IUSE/PFE: RED) grant, our vision is to focus on faculty development and culture change to reduce the effort and risk experienced by faculty in implementing pedagogical changes and to increase iterative, datadriven changes in teaching. Our project, called Teams for Creating Opportunities for Revolutionizing the Preparation of Students (TCORPS), is an adaptation of the “Additive innovation” model proposed by Arizona State University [1]. The Department of Mechanical Engineering at Texas A&M University has a long legacy of individualistic andin many casesa fixed mindset [2] approach to teaching with the expectation of topdown management of change. The goal of our project is to evolve the departmental culture to a bottomup team structure where the faculty embrace an innovative mindset and extend an iterative buildtestlearn method of the maker culture [3] that was formalized by the Lean Startup [4] approach. Faculty already have investigative and experimentationdriven processes in place for research and a keen understanding of data to support their hypotheses. We aim to leverage this preexisting strength and knowledge by extending it to the facultyled, smallscale, iterative improvement of curriculum and pedagogyFree, publiclyaccessible full text available July 1, 2023

This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The model couples the following two components: (1) the vector representations of local contents of images and (2) the matrix representations of local pixel displacements caused by the relative motions between the agent and the objects in the 3D scene. When the image frame undergoes changes due to local pixel displacements, the vectors are multiplied by the matrices that represent the local displacements. Thus the vector representation is equivariant as it varies according to the local displacements. Our experiments show that our model can learn Gaborlike filter pairs of quadrature phases. The profiles of the learned filters match those of simple cells in Macaque V1. Moreover, we demonstrate that the model can learn to infer local motions in either a supervised or unsupervised manner. With such a simple model, we achieve competitive results on optical flow estimation.

Learning energybased model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in highdimensional data space is generally not mixing, because the energy function, which is usually parametrized by deep network, is highly multimodal in the data space. This is a serious handicap for both theory and practice of EBMs. In this paper, we propose to learn EBM with a flowbased model (or in general latent variable model) serving as a backbone, so that the EBM is a correction or an exponential tilting of the flowbased model. We show that the model has a particularly simple form in the space of the latent variables of the generative model, and MCMC sampling of the EBM in the latent space mixes well and traverses modes in the data space. This enables proper sampling and learning of EBMs.

Latent space EnergyBased Models (EBMs), also known as energybased priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built upon it have made interesting attempts aiming at the interpretability of text modeling. However, latent space EBMs also inherit some flaws from EBMs in data space; the degenerate MCMC sampling quality in practice can lead to poor generation quality and instability in training, especially on data with complex latent structures. Inspired by the recent efforts that leverage diffusion recovery likelihood learning as a cure for the sampling issue, we introduce a novel symbiosis between the diffusion models and latent space EBMs in a variational learning framework, coined as the latent diffusion energybased model. We develop a geometric clusteringbased regularization jointly with the information bottleneck to further improve the quality of the learned latent space. Experiments on several challenging tasks demonstrate the superior performance of our model on interpretable text modeling over strong counterparts.

While energybased models (EBMs) exhibit a number of desirable properties, training and sampling on highdimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion re covery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing re covery likelihood is more tractable than marginal likelihood, as sampling from the conditional distributions is much easier than sampling from the marginal distribu tions. After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution and progressively samples the conditional distributions at decreasingly lower noise levels. Our method gener ates high fidelity samples on various image datasets. On unconditional CIFAR10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs. Moreover, we demonstrate that unlike previous work on EBMs, our longrun MCMC samples from the conditional distributions do not diverge and still represent realistic images, allowing us to accurately estimate the normalized density of datamore »

How to effectively represent camera pose is an essential problem in 3D computer vision, especially in tasks such as camera pose regression and novel view synthesis. Traditionally, 3D position of the camera is represented by Cartesian coordinate and the orientation is represented by Euler angle or quaternions. These representations are manually designed, which may not be the most effective representation for downstream tasks. In this work, we propose an approach to learn neural representations of camera poses and 3D scenes, coupled with neural representations of local camera movements. Specifically, the camera pose and 3D scene are represented as vectors and the local camera movement is represented as a matrix operating on the vector of the camera pose. We demonstrate that the camera movement can further be parametrized by a matrix Lie algebra that underlies a rotation system in the neural space. The vector representations are then concatenated and generate the posed 2D image through a decoder network. The model is learned from only posed 2D images and corresponding camera poses, without access to depths or shapes. We conduct extensive experiments on synthetic and real datasets. The results show that compared with other camera pose representations, our learned representation is moremore »

Understanding how grid cells perform path integration calculations remains a fundamental problem. In this paper, we conduct theoretical analysis of a general representation model of path integration by grid cells, where the 2D selfposition is encoded as a higher dimensional vector, and the 2D selfmotion is represented by a general transformation of the vector. We identify two conditions on the transformation. One is a group representation condition that is necessary for path integration. The other is an isotropic scaling condition that ensures locally conformal embedding, so that the error in the vector representation translates conformally to the error in the 2D selfposition. Then we investigate the simplest transformation, i.e., the linear transformation, uncover its explicit algebraic and geometric structure as matrix Lie group of rotation, and explore the connection between the isotropic scaling condition and a special class of hexagon grid patterns. Finally, with our optimizationbased approach, we manage to learn hexagon grid patterns that share similar properties of the grid cells in the rodent brain. The learned model is capable of accurate long distance path integration. Code is available at https://github.com/ruiqigao/gridcellpath.

Dielectrophoresis is a force applied to microparticles in nonuniform electric field. The presented study discusses the fabrication of the glassy carbon interdigitated microelectrode arrays using lithography process based on lithographic patterning and subsequent pyrolysis of negative SU8 photoresist. Resulting high resistance electrodes would have the regions of high electric field at the ends of microarray as demonstrated by simulation. The study demonstrates that combining the AC applied bias with the DC offset allows the user to separate subpopulations of microparticulates and control the propulsion of microparticles to the high field areas such as the ends of the electrode array. The direction of the movement of the particles can be switched by changing the offset. The demonstrated novel integrated DEP separation and propulsion can be applied to various fields including invitro diagnostics as well as to microassembly technologies.