Sparse matrix-dense vector (SpMV) multiplication is inherent in
most scientific, neural networks and machine learning algorithms.
To efficiently exploit sparsity of data in the SpMV computations,
several compressed data representations have been used. However,
the compressed data representations of sparse date can result in
overheads for locating nonzero values, requiring indirect memory
accesses and increased instruction count and memory access delays.
We call these translations of compressed representations as
metadata processing. We propose a memory-side accelerator for
metadata (or indexing) computations and supplying only the required
nonzero values to the processor, additionally permitting an
overlap of indexing with core computations on nonzero elements.
In this contribution, we target our accelerator for low-end microcontrollers
with very limited memory and processing capabilities.
In this paper we will explore two dedicated ASIC designs of the
proposed accelerator that handles the indexed memory accesses for
compressed sparse row (CSR) format working alongside a simple
RISC-like programmable core. One version of the the accelerator
supplies only vector values corresponding to nonzero matrix values
and the second version supplies both nonzero matrix and matching
vector values for SpMV computations. Our experiments show
speedups ranging between 1.3 and 2.1 times for SpMV for different
levels of sparsities. Our accelerator also results in energy savings
ranging between 15.8% and 52.7% over different matrix sizes, when
compared to the baseline system with primary RISC-V core performing
all computations. We use smaller synthetic matrices with
different sparsities and larger real-world matrices with higher sparsities
(below 1% non-zeros) in our experimental evaluations.
more »
« less
Improving measurements of similarity judgments with machine-learning algorithms
Intertemporal choices involve assessing options with different reward amounts available at different time delays. The similarity approach to intertemporal choice focuses on judging how similar amounts and delays are. Yet we do not fully understand the cognitive process of how these judgments are made. Here, we use machine-learning algorithms to predict similarity judgments to (1) investigate which algorithms best predict these judgments, (2) assess which predictors are most useful in predicting participants’ judgments, and (3) determine the minimum number of judgments required to accurately predict future judgments. We applied eight algorithms to similarity judgments for reward amount and time delay made by participants in two data sets. We found that neural network, random forest, and support vector machine algorithms generated the highest out-of-sample accuracy. Though neural networks and support vector machines offer little clarity in terms of a possible process for making similarity judgments, random forest algorithms generate decision trees that can mimic the cognitive computations of human judgment making. We also found that the numerical difference between amount values or delay values was the most important predictor of these judgments, replicating previous work. Finally, the best performing algorithms such as random forest can make highly accurate predictions of judgments with relatively small sample sizes (~ 15), which will help minimize the numbers of judgments required to extrapolate to new value pairs. In summary, machine-learning algorithms provide both theoretical improvements to our understanding of the cognitive computations involved in similarity judgments and intertemporal choices as well as practical improvements in designing better ways of collecting data.
more »
« less
- Award ID(s):
- 1658837
- NSF-PAR ID:
- 10211595
- Date Published:
- Journal Name:
- Journal of Computational Social Science
- ISSN:
- 2432-2717
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Predicting polycystic ovary syndrome with machine learning algorithms from electronic health recordsmore » « less
Introduction Predictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis.
Methods This is a retrospective cohort study from a SafetyNet hospital’s electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound.
Results We developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved an average AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG.
Conclusion Machine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary.
-
more » « less
Abstract Study Objectives Dementia is a growing cause of disability and loss of independence in the elderly, yet remains largely underdiagnosed. Early detection and classification of dementia can help close this diagnostic gap and improve management of disease progression. Altered oscillations in brain activity during sleep are an early feature of neurodegenerative diseases and be used to identify those on the verge of cognitive decline.
Methods Our observational cross-sectional study used a clinical dataset of 10 784 polysomnography from 8044 participants. Sleep macro- and micro-structural features were extracted from the electroencephalogram (EEG). Microstructural features were engineered from spectral band powers, EEG coherence, spindle, and slow oscillations. Participants were classified as dementia (DEM), mild cognitive impairment (MCI), or cognitively normal (CN) based on clinical diagnosis, Montreal Cognitive Assessment, Mini-Mental State Exam scores, clinical dementia rating, and prescribed medications. We trained logistic regression, support vector machine, and random forest models to classify patients into DEM, MCI, and CN groups.
Results For discriminating DEM versus CN, the best model achieved an area under receiver operating characteristic curve (AUROC) of 0.78 and area under precision-recall curve (AUPRC) of 0.22. For discriminating MCI versus CN, the best model achieved an AUROC of 0.73 and AUPRC of 0.18. For discriminating DEM or MCI versus CN, the best model achieved an AUROC of 0.76 and AUPRC of 0.32.
Conclusions Our dementia classification algorithms show promise for incorporating dementia screening techniques using routine sleep EEG. The findings strengthen the concept of sleep as a window into neurodegenerative diseases.
-
more » « less
Abstract Previous work using logistic regression suggests that cognitive control‐related frontoparietal activation in early psychosis can predict symptomatic improvement after 1 year of coordinated specialty care with 66% accuracy. Here, we evaluated the ability of six machine learning (ML) algorithms and deep learning (DL) to predict “Improver” status (>20% improvement on Brief Psychiatric Rating Scale [BPRS] total score at 1‐year follow‐up vs. baseline) and continuous change in BPRS score using the same functional magnetic resonance imaging‐based features (frontoparietal activations during the AX‐continuous performance task) in the same sample (individuals with either schizophrenia (
n = 65, 49M/16F, mean age 20.8 years) or Type I bipolar disorder (n = 17, 9M/8F, mean age 21.6 years)). 138 healthy controls were included as a reference group. “Shallow” ML methods included Naive Bayes, support vector machine, K Star, AdaBoost, J48 decision tree, and random forest. DL included an explainable artificial intelligence (XAI) procedure for understanding results. The best overall performances (70% accuracy for the binary outcome and root mean square error = 9.47 for the continuous outcome) were achieved using DL. XAI revealed left DLPFC activation was the strongest feature used to make binary classification decisions, with a classification activation threshold (adjusted beta = .017) intermediate to the healthy control mean (adjusted beta = .15, 95% CI = −0.02 to 0.31) and patient mean (adjusted beta = −.13, 95% CI = −0.37 to 0.11). Our results suggest DL is more powerful than shallow ML methods for predicting symptomatic improvement. The left DLPFC may be a functional target for future biomarker development as its activation was particularly important for predicting improvement. -
Objective Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73–0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s42001-020-00098-1
