Browsing by Author "Baraniuk, Richard"
Now showing 1 - 20 of 33
Results Per Page
Sort Options
Item A Data and Platform-Aware Framework For Large-Scale Machine Learning(2015-04-24) Mirhoseini, Azalia; Koushanfar, Farinaz; Aazhang, Behnaam; Baraniuk, Richard; Jermaine, ChristopherThis thesis introduces a novel framework for execution of a broad class of iterative machine learning algorithms on massive and dense (non-sparse) datasets. Several classes of critical and fast-growing data, including image and video content, contain dense dependencies. Current pursuits are overwhelmed by the excessive computation, memory access, and inter-processor communication overhead incurred by processing dense data. On the one hand, solutions that employ data-aware processing techniques produce transformations that are oblivious to the overhead created on the underlying computing platform. On the other hand, solutions that leverage platform-aware approaches do not exploit the non-apparent data geometry. My work is the first to develop a comprehensive data- and platform-aware solution that provably optimizes the cost (in terms of runtime, energy, power, and memory usage) of iterative learning analysis on dense data. My solution is founded on a novel tunable data transformation methodology that can be customized with respect to the underlying computing resources and constraints. My key contributions include: (i) introducing a scalable and parametric data transformation methodology that leverages coarse-grained parallelism in the data to create versatile and tunable data representations, (ii) developing automated methods for quantifying platform-specific computing costs in distributed settings, (iii) devising optimally-bounded partitioning and distributed flow scheduling techniques for running iterative updates on dense correlation matrices, (iv) devising methods that enable transforming and learning on streaming dense data, and (v) providing user-friendly open-source APIs that facilitate adoption of my solution on multiple platforms including (multi-core and many-core) CPUs and FPGAs. Several learning algorithms such as regularized regression, cone optimization, and power iteration can be readily solved using my APIs. My solutions are evaluated on a number of learning applications including image classification, super-resolution, and denoising. I perform experiments on various real-world datasets with up to 5 billion non-zeros on a range of computing platforms including Intel i7 CPUs, Amazon EC2, IBM iDataPlex, and Xilinx Virtex-6 FPGAs. I demonstrate that my framework can achieve up to 2 orders of magnitude performance improvement in comparison with current state-of-the-art solutions.Item A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science Principles(2024-07-22) Liu, Lucy; Baraniuk, RichardIntelligent Tutoring Systems (ITS) have gained popularity due to their ability to provide students with cost-effective and personalized learning experience. The development of Large Language Models (LLMs) offer great potential to revolutionize personalized education to autonomously create effective ITS without relying on manual, labor intensive processes. Our research introduces a novel design framework, named Conversational Learning with Analytical Step-by-Step Strategies (CLASS), which harnesses the potential of high-performance LLMs to construct advanced ITS. The CLASS framework empowers ITS with two critical capabilities. First, through a carefully curated scaffolding dataset, CLASS provides essential problem-solving capabilities, enabling it to provide tutor-like, step-by-step guidance to students. Second, by using a dynamic conversational dataset, CLASS facilitates natural language interactions, which fosters engaging student-tutor conversations. The CLASS framework also enhances the transparency of ITS, offering valuable insights into its internal decision-making process. This interpretability allows seamless integration of user feedback, thus facilitating continuous refinement and improvement. Additionally, we present a practical application of the CLASS framework through a proof-of-concept ITS, with a focus on introductory college-level biology content. A carefully constructed protocol was developed for the biology ITS's preliminary evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting its capability to break down questions into manageable subproblems and provide encouraging responses to students.Item A Resource-Aware Streaming-based Framework for Big Data Analysis(2015-12-02) Darvish Rouhani, Bita; Koushanfar, Farinaz; Aazhang, Behnaam; Baraniuk, RichardThe ever growing body of digital data is challenging conventional analytical techniques in machine learning, computer vision, and signal processing. Traditional analytical methods have been mainly developed based on the assumption that designers can work with data within the confines of their own computing environment. The growth of big data, however, is changing that paradigm especially in scenarios where severe memory and computational resource constraints exist. This thesis aims at addressing major challenges in big data learning problem by devising a new customizable computing framework that holistically takes into account the data structure and underlying platform constraints. It targets a widely used class of analytical algorithms that model the data dependencies by iteratively updating a set of matrix parameters, including but not limited to most regression methods, expectation maximization, and stochastic optimizations, as well as the emerging deep learning techniques. The key to our approach is a customizable, streaming-based data projection methodology that adaptively transforms data into a new lower-dimensional embedding by simultaneously considering both data and hardware characteristics. It enables scalable data analysis and rapid prototyping of an arbitrary matrix-based learning task using a sparse-approximation of the collection that is constantly updated inline with the data arrival. Our work is supported by a set of user-friendly Application Programming Interfaces (APIs) that ensure automated adaptation of the proposed framework to various datasets and System on Chip (SoC) platforms including CPUs, GPUs, and FPGAs. Proof of concept evaluations using a variety of large contemporary datasets corroborate the practicability and scalability of our approach in resource-limited settings. For instance, our results demonstrate 50-fold improvement over the best known prior-art in terms of memory, energy, power, and runtime for training and execution of deep learning models in deployment of different sensing applications including indoor localization and speech recognition on constrained embedded platforms used in today's IoT enabled devices such as autonomous vehicles, robots, and smartphone.Item An Introduction to Compressive Sensing(Rice University, 2014-08-26) Baraniuk, Richard; Davenport, Mark A.; Duarte, Marco F.; Hegde, ChinmayItem Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning(Springer Nature, 2020) Seydoux, Léonard; Balestriero, Randall; Poli, Piero; de Hoop, Maarten; Campillo, Michel; Baraniuk, RichardThe continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas.Item Compressive Sensing(Rice University, 2007-09-21) Davenport, Mark A.; Baraniuk, Richard; DeVore, RonaldItem Continuous-Time Signals and Systems(Rice University, 2018-10-03) Baraniuk, Richard; Moravec, MatthewItem Conveying language through haptics: a multi-sensory approach(ACM, 2018) Dunkelberger, Nathan; Sullivan, Jenny; Bradley, Joshua; Walling, Nickolas P.; Manickam, Indu; Dasarathy, Gautam; Israr, Ali; Lau, Frances W.Y.; Klumb, Keith; Knott, Brian; Abnousi, Freddy; Baraniuk, Richard; O'Malley, Marcia K.In our daily lives, we rely heavily on our visual and auditory channels to receive information from others. In the case of impairment, or when large amounts of information are already transmitted visually or aurally, alternative methods of communication are needed. A haptic language offers the potential to provide information to a user when visual and auditory channels are unavailable. Previously created haptic languages include deconstructing acoustic signals into features and displaying them through a haptic device, and haptic adaptations of Braille or Morse code; however, these approaches are unintuitive, slow at presenting language, or require a large surface area. We propose using a multi-sensory haptic device called MISSIVE, which can be worn on the upper arm and is capable of producing brief cues, sufficient in quantity to encode the full English phoneme set. We evaluated our approach by teaching subjects a subset of 23 phonemes, and demonstrated an 86% accuracy in a 50 word identification task after 100 minutes of training.Item Current progress and open challenges for applying deep learning across the biosciences(Springer Nature, 2022) Sapoval, Nicolae; Aghazadeh, Amirali; Nute, Michael G.; Antunes, Dinler A.; Balaji, Advait; Baraniuk, Richard; Barberan, C.J.; Dannenfelser, Ruth; Dun, Chen; Edrisi, Mohammadamin; Elworth, R.A. Leo; Kille, Bryce; Kyrillidis, Anastasios; Nakhleh, Luay; Wolfe, Cameron R.; Yan, Zhi; Yao, Vicky; Treangen, Todd J.Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.Item Discrete-Time Signals and Systems(Rice University, 2018-10-03) Baraniuk, Richard; Moravec, MatthewItem ECE 301 Projects Fall 2003(Rice University, 2011-04-22) Husband, Mark; Galvan, Adan; Reedstrom, Charlet; Baraniuk, RichardTeam Projects created for the ECE 301, Fall 2003.Item EDoF-ToF: extended depth of field time-of-flight imaging(Optical Society of America, 2021) Tan, Jasper; Boominathan, Vivek; Baraniuk, Richard; Veeraraghavan, AshokConventional continuous-wave amplitude-modulated time-of-flight (CWAM ToF) cameras suffer from a fundamental trade-off between light throughput and depth of field (DoF): a larger lens aperture allows more light collection but suffers from significantly lower DoF. However, both high light throughput, which increases signal-to-noise ratio, and a wide DoF, which enlarges the system’s applicable depth range, are valuable for CWAM ToF applications. In this work, we propose EDoF-ToF, an algorithmic method to extend the DoF of large-aperture CWAM ToF cameras by using a neural network to deblur objects outside of the lens’s narrow focal region and thus produce an all-in-focus measurement. A key component of our work is the proposed large-aperture ToF training data simulator, which models the depth-dependent blurs and partial occlusions caused by such apertures. Contrary to conventional image deblurring where the blur model is typically linear, ToF depth maps are nonlinear functions of scene intensities, resulting in a nonlinear blur model that we also derive for our simulator. Unlike extended DoF for conventional photography where depth information needs to be encoded (or made depth-invariant) using additional hardware (phase masks, focal sweeping, etc.), ToF sensor measurements naturally encode depth information, allowing a completely software solution to extended DoF. We experimentally demonstrate EDoF-ToF increasing the DoF of a conventional ToF system by 3.6 ×, effectively achieving the DoF of a smaller lens aperture that allows 22.1 × less light. Ultimately, EDoF-ToF enables CWAM ToF cameras to enjoy the benefits of both high light throughput and a wide DoF.Item ELEC 301 Projects Fall 2004(Rice University, 2010-05-07) Baraniuk, RichardTeam Projects created for ELEC 301, Fall 2004.Item ELEC 301 Projects Fall 2005(Rice University, 2008-07-09) Baraniuk, RichardTeam Projects created for ELEC 301, Fall 2005.Item Fast Alternating Direction Optimization Methods(Society for Industrial and Applied Mathematics, 2014) Goldstein, Tom; O’Donoghue, Brendan; Setzer, Simon; Baraniuk, RichardAlternating direction methods are a common tool for general mathematical programming and optimization. These methods have become particularly important in the field of variational image processing, which frequently requires the minimization of nondifferentiable objectives. This paper considers accelerated (i.e., fast) variants of two common alternating direction methods: the alternating direction method of multipliers (ADMM) and the alternating minimization algorithm (AMA). The proposed acceleration is of the form first proposed by Nesterov for gradient descent methods. In the case that the objective function is strongly convex, global convergence bounds are provided for both classical and accelerated variants of the methods. Numerical examples are presented to demonstrate the superior performance of the fast methods for a wide variety of problems.Item Fast, Exact Synthesis of Gaussian and nonGaussian Long-Range-Dependent Processes(2009-04-15) Baraniuk, Richard; Crouse, Matthew1/f noise and statistically self-similar random processes such as fractional Brownian motion (fBm) and fractional Gaussian noise (fGn) are fundamental models for a host of real-world phenomena, from network traffic to DNA to the stock market. Synthesis algorithms play a key role by providing the feedstock of data necessary for running complex simulations and accurately evaluating analysis techniques. Unfortunately, current algorithms to correctly synthesize these long-range dependent (LRD) processes are either abstruse or prohibitively costly, which has spurred the wide use of inexact approximations. To fill the gap, we develop a simple, fast (O(N logN) operations for a length-N signal) framework for exactly synthesizing a range of Gaussian and nonGaussian LRD processes. As a bonus, we introduce and study a new bi-scaling fBm process featuring a "kinked" correlation function that exhibits distinct scaling laws at coarse and fine scales.Item Filter Design - Sidney Burrus Style(Rice University, 2012-11-17) Baraniuk, RichardHow Sidney Burrus would design an analog filter.Item Lensless imaging device for microscopy and fingerprint biometric(2020-08-25) Veeraraghavan, Ashok; Baraniuk, Richard; Robinson, Jacob; Boominathan, Vivek; Adams, Jesse; Avants, Benjamin; Rice University; United States Patent and Trademark OfficeIn one aspect, embodiments disclosed herein relate to a lens-free imaging system. The lens-free imaging system includes: an image sampler, a radiation source, a mask disposed between the image sampler and a scene, and an image sampler processor. The image sampler processor obtains signals from the image sampler that is exposed, through the mask, to radiation scattered by the scene which is illuminated by the radiation source. The image sampler processor then estimates an image of the scene based on the signals from the image sampler, processed using a transfer function that relates the signals and the scene.Item Lensless imaging system using an image sensor with one or more attenuating layers(2021-11-16) Sankaranarayanan, Aswin; Veeraraghavan, Ashok; Hendricks, Lisa A.; Baraniuk, Richard; Ayremlou, Ali; Asif, Salman M.; Rice University; United States Patent and Trademark OfficeA lens-free imaging system for generating an image of a scene includes an electromagnetic (EM) radiation sensor; a mask disposed between the EM radiation sensor and the scene; an image processor that obtains signals from the EM radiation sensor while the EM radiation sensor is exposed to the scene; and estimates the image of the scene based on, at least in part, the signals and a transfer function between the scene and the EM radiation sensor.Item Leveraging Physics-based Models in Data-driven Computational Imaging(2019-04-19) Chen, George; Veeraraghavan, Ashok; Baraniuk, Richard; Shrivastava, AnshumaliDeep Learning (DL) has revolutionized various applications in computational imaging and computer vision. However, existing DL frameworks are mostly data-driven, which largely disregards decades of prior work that focused on signal processing theory and physics-based models. As a result, many DL based image reconstruction methods generate eye-pleasing results but faces strong drawbacks, including 1) output not being physically correct, 2) requiring large datasets with labor-intensive annotations. In the thesis, we propose several computational imaging frameworks that leverage both physics-based models and data-driven deep learning. By formulating the physical model as an integrated and differentiable layer of the larger learning networks, we are able to a) constraint the results to be closer to the physical reality, b) perform self-supervised network training using the physical constraints as loss functions, avoiding manually labeled data, and c) develop true end-to-end imaging systems with jointly optimized front-end sensors and back-end algorithms. In particular, we show that the proposed approach is suitable for a wide range of applications, including motion de-blurring, 3D imaging and super-resolution microscopy.