Search Results for author:
Found 39 papers, 4 papers with code
Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale
In this paper, we study the aggregate effect of power-capping GPUs on GPU temperature and power draw at a research supercomputing center.
Lincoln AI Computing Survey (LAICS) Update
Finally, a brief description of each of the new accelerators that have been added in the survey this year is included.
From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference
Large language models (LLMs) have exploded in popularity due to their new generative capabilities that go far beyond prior state-of-the-art.
Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection
We first pretrain these factor matrices on the RGB modality, for which plenty of training data are assumed to exist and then augment only a few trainable parameters for training on the IR modality to avoid over-fitting, while encouraging them to capture complementary cues from those trained only on the RGB modality.
Pixel-Grounded Prototypical Part Networks
Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning.
A Green(er) World for A.I
applications, we are sure to face an ever-mounting energy footprint to sustain these computational budgets, data storage needs, and more.
An Evaluation of Low Overhead Time Series Preprocessing Techniques for Downstream Machine Learning
Our best performing models achieve a classification accuracy greater than 95%, outperforming previous approaches to multi-channel time series classification with the MIT SuperCloud Dataset by 5%.
The MIT Supercloud Workload Classification Challenge
We introduce a labelled dataset that can be used to develop new approaches to workload classification and present initial results based on existing approaches.
Converse: A Tree-Based Modular Task-Oriented Dialogue System
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
Benchmarking Resource Usage for Efficient Distributed Deep Learning
Deep learning (DL) workflows demand an ever-increasing budget of compute and energy in order to achieve outsized gains.
Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution
The distribution gap between training datasets and data encountered in production is well acknowledged.
AI Accelerator Survey and Trends
Over the past several years, new machine learning accelerators were being announced and released every month for a variety of applications from speech recognition, video object detection, assisted driving, and many data center applications.
Maneuver Identification Challenge
The Maneuver Identification Challenge hosted at maneuver-id. mit. edu provides thousands of trajectories collected from pilots practicing in flight simulators, descriptions of maneuvers, and examples of these maneuvers performed by experienced pilots.
The MIT Supercloud Dataset
In this paper we introduce the MIT Supercloud Dataset which aims to foster innovative AI/ML approaches to the analysis of large scale HPC and datacenter/cloud operations.
To Boost or not to Boost: On the Limits of Boosted Neural Networks
Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate.
Model Compression Using Optimal Transport
Model compression methods are important to allow for easier deployment of deep learning models in compute, memory and energy-constrained environments such as mobile phones.
Multi-head Knowledge Distillation for Model Compression
We add loss terms for training the student that measure the dissimilarity between student and teacher outputs of the auxiliary classifiers.
Survey of Machine Learning Accelerators
New machine learning accelerators are being announced and released each month for a variety of applications from speech recognition, video object detection, assisted driving, and many data center applications.
Compute, Time and Energy Characterization of Encoder-Decoder Networks with Automatic Mixed Precision Training
In this paper we examine the compute, energy and time costs of training a UNet based deep neural network for the problem of predicting short term weather forecasts (called precipitation Nowcasting).
Benchmarking network fabrics for data distributed training of deep neural networks
The large computational requirements for training deep models have necessitated the development of new methods for faster training.
Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks via Nonlinear Multigrid
A Multigrid Full Approximation Storage algorithm for solving Deep Residual Networks is developed to enable neural network parallelized layer-wise training and concurrent computational kernel execution on GPUs.
LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities.
Ranked #1 on
Face Alignment
on Menpo
GraphChallenge.org Sparse Deep Neural Network Performance
The Sparse Deep Neural Network (DNN) Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a challenge that is reflective of emerging sparse AI systems.
GraphChallenge.org Triangle Counting Performance
In 2017, 2018, and 2019 many triangle counting submissions were received from a wide range of authors and organizations.
Distributed, Parallel, and Cluster Computing Performance
Sparse Deep Neural Network Graph Challenge
The Sparse DNN Challenge is based on a mathematically well-defined DNN inference computation and can be implemented in any programming environment.
Survey and Benchmarking of Machine Learning Accelerators
Advances in multicore processors and accelerators have opened the flood gates to greater exploration and application of machine learning techniques to a variety of applications.
Performance B.8; C.4
Securing HPC using Federated Authentication
Federated authentication can drastically reduce the overhead of basic account maintenance while simultaneously improving overall system security.
Distributed, Parallel, and Cluster Computing Cryptography and Security
Streaming 1.9 Billion Hypersparse Network Updates per Second with D4M
This work describes the design and performance optimization of an implementation of hierarchical associative arrays that reduces memory pressure and dramatically increases the update rate into an associative array.
Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
Face super-resolution methods usually aim at producing visually appealing results rather than preserving distinctive features for further face identification.
Street Scene: A new dataset and evaluation protocol for video anomaly detection
Progress in video anomaly detection research is currently slowed by small datasets that lack a wide variety of activities as well as flawed evaluation criteria.
TabulaROSA: Tabular Operating System Architecture for Massively Parallel Heterogeneous Compute Engines
In this context, an operating system can be viewed as software that brokers and tracks the resources of the compute engines and is akin to a database management system.
Distributed, Parallel, and Cluster Computing Databases Operating Systems Performance
Querying Word Embeddings for Similarity and Relatedness
Word embeddings obtained from neural network models such as Word2Vec Skipgram have become popular representations of word meaning and have been evaluated on a variety of word similarity and relatedness norming data.
Static Graph Challenge: Subgraph Isomorphism
The proposed Subgraph Isomorphism Graph Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a graph challenge that is reflective of many real-world graph analytics processing systems.
Distributed, Parallel, and Cluster Computing Data Structures and Algorithms
An Artificial Language Evaluation of Distributional Semantic Models
Recent studies of distributional semantic models have set up a competition between word embeddings obtained from predictive neural networks and word vectors obtained from abstractive count-based models.
Benchmarking Data Analysis and Machine Learning Applications on the Intel KNL Many-Core Processor
Thus, the performance of these applications on KNL systems is of high interest to LLSC users and the broader data analysis and machine learning communities.
Performance Instrumentation and Methods for Astrophysics Distributed, Parallel, and Cluster Computing Computational Physics
A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection
We present a multi-stream bi-directional recurrent neural network for fine-grained action detection.
Action Recognition In Videos
Fine-Grained Action Detection
+2
An Improved Deep Learning Architecture for Person Re-Identification
Novel elements of our architecture include a layer that computes cross-input neighborhood differences, which capture local relationships among mid-level features that were computed separately from the two input images.
Real-Time 3D Head Pose and Facial Landmark Estimation From Depth Images Using Triangular Surface Patch Features
The matched triangular surface patches in the training set are used to compute estimates of the 3D head pose and facial landmark positions in the input depth map.
Rapid Object Detection using a Boosted Cascade of Simple Features
The first is the introduction of a new image representation called the “Integral linage” which allows the features used by our detector to be computed very quickly.
