Josh Gardner

Josh Gardner

Auto-generated profile, based on publicly available information

Josh Gardner

University of Michigan

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2018 in User Modeling and User-Adapted Interaction
Verified
Journal Article
Closed access
PDF file
JGJosh Gardner
Josh Gardner
CBChristopher Brooks
Christopher Brooks

12 June 2023
Verified
Conference Paper
Open access
JGJoshua Gardner
Joshua Gardner
RYRenzhe Yu
Renzhe Yu
QNQuan Nguyen
Quan Nguyen
CBChristopher Brooks
Christopher Brooks
RKRene Kizilcec
Rene Kizilcec
Modern machine learning increasingly supports paradigms that are multi-institutional (using data from multiple institutions during training) or cross-institutional (using models from multiple institutions for inference), but the empirical effects of these paradigms are not well understood. This study investigates cross-institutional learning via an empirical case study in higher education. We propose a framework and metrics for assessing the utility and fairness of student dropout prediction models that are transferred across institutions. We examine the feasibility of cross-institutional transfer under real-world data- and model-sharing constraints, quantifying model biases for intersectional student identities, characterizing potential disparate impact due to these biases, and investigating the impact of various cross-institutional ensembling approaches on fairness and overall model performance. We perform this analysis on data representing over 200,000 enrolled students annually from four universities without sharing training data between institutions. We find that a simple zero-shot cross-institutional transfer procedure can achieve similar performance to locally-trained models for all institutions in our study, without sacrificing model fairness. We also find that stacked ensembling provides no additional benefits to overall performance or fairness compared to either a local model or the zero-shot transfer procedure we tested. We find no evidence of a fairness-accuracy tradeoff across dozens of models and transfer schemes evaluated. Our auditing procedure also highlights the importance of intersectional fairness analysis, revealing performance disparities at the intersection of sensitive identity groups that are concealed under one-dimensional analysis.1

1 May 2020
Verified
Conference Paper
Closed access
GHGlenn Henry
Glenn Henry
PPParviz Palangpour
Parviz Palangpour
MTMichael Thomson
Michael Thomson
JGJ Scott Gardner
J Scott Gardner
BABryce Arden
Bryce Arden
TWTyler Walker
Tyler Walker
Demand for high performance deep learning (DL) inference in software applications is growing rapidly. DL workloads run on myriad platforms, including general purpose processors (CPU), system-on-chip (SoC) with accelerators, graphics processing units (GPU), and neural processing unit (NPU) addin cards. DL software engineers typically must choose between relatively slow general hardware (e.g., CPUs, SoCs) or relatively expensive, large, power-hungry hardware (e.g., GPUs, NPUs). This paper describes Centaur Technology’s Ncore, the industry’s first high-performance DL coprocessor technology integrated into an x86 SoC with server-class CPUs. Ncore’s 4096 byte-wide SIMD architecture supports INT8, UINT8, INT16, and BF16 datatypes, with 20 tera-operations-per-second compute capability. Ncore shares the SoC ring bus for low-latency communication and work sharing with eight 64-bit x86 cores, offering flexible support for new and evolving models. The x86 SoC platform can further scale out performance via multiple sockets, systems, or third-party PCIe accelerators. Ncore’s software stack automatically converts quantized models for Ncore consumption and leverages existing DL frameworks. In MLPerf’s Inference v0.5 closed division benchmarks, Ncore achieves 1218 IPS throughput and 1.05ms latency on ResNet-50v1.5 and achieves lowest latency of all Mobilenet-V1 submissions $(329 \mu \mathrm{s})$. Ncore yields 23x speedup over other x86 vendor percore throughput, while freeing its own x86 cores for other work. Ncore is the only integrated solution among the memory intensive neural machine translation (NMT) submissions.

18 November 2018 in Journal of Learning Analytics
Verified
Journal Article
Open access
PDF file
JGJoshua Patrick Gardner
Joshua Patrick Gardner
CBChristopher Brooks
Christopher Brooks
WLWarren Li
Warren Li
In this paper, we evaluate the complete undergraduate co-enrollment network over a decade of education at a large American public university. We provide descriptive and exploratory analyses of the network, demonstrating that the co-enrollment networks evaluated follow power-law degree distributions similar to many other large-scale networks; that they reveal strong performance-based assortativity; and that network-based features can improve GPA-based student performance predictors. We model the university-wide undergraduate co-enrollment network as an undirected graph, and implement multiple network-augmented approaches to student grade prediction, including an adaption of the structural modelling approach from (Getoor, 2005, Lu, 2003}. We compare the performance of this predictor to traditional methods used for grade prediction in undergraduate university courses, and demonstrate that a multi-view ensembling approach outperforms both prior ``flat'' and network-based models for grade prediction across several classification metrics. These findings demonstrate the usefulness of combining diverse approaches in models of student success, and demonstrate specific network-based modelling strategies that are likely to be most effective for grade prediction.

10 July 2018 in arXiv
Verified
Preprint
Open access
PDF file
JGJosh Gardner
Josh Gardner
YYYuming Yang
Yuming Yang
RBRyan Baker
Ryan Baker
CBChristopher Brooks
Christopher Brooks
The use of machine learning techniques has expanded in education research, driven by the rich data from digital learning environments and institutional data warehouses. However, replication of machine learned models in the domain of the learning sciences is particularly challenging due to a confluence of experimental, methodological, and data barriers. We discuss the challenges of end-to-end machine learning replication in this context, and present an open-source software toolkit, the MOOC Replication Framework (MORF), to address them. We demonstrate the use of MORF by conducting a replication at scale, and provide a complete executable container, with unique DOIs documenting the configurations of each individual trial, for replication or future extension at https://github.com/educational-technology-collective/fy2015-replication. This work demonstrates an approach to end-to-end machine learning replication which is relevant to any domain with large, complex or multi-format, privacy-protected data with a consistent schema.

13 June 2018 in arXiv
Verified
Preprint
Open access
PDF file
JGJosh Gardner
Josh Gardner
CBChristopher Brooks
Christopher Brooks
Model evaluation -- the process of making inferences about the performance of predictive models -- is a critical component of predictive modeling research in learning analytics. We survey the state of the practice with respect to model evaluation in learning analytics, which overwhelmingly uses only naive methods for model evaluation or statistical tests which are not appropriate for predictive model evaluation. We conduct a critical comparison of both null hypothesis significance testing (NHST) and a preferred Bayesian method for model evaluation. Finally, we apply three methods -- the na{\"i}ve average commonly used in learning analytics, NHST, and Bayesian -- to a predictive modeling experiment on a large set of MOOC data. We compare 96 different predictive models, including different feature sets, statistical modeling algorithms, and tuning hyperparameters for each, using this case study to demonstrate the different experimental conclusions these evaluation techniques provide.