Search Results for author:
Found 27 papers, 6 papers with code
Unseen Object Reasoning with Shared Appearance Cues
Our paper introduces a straightforward yet elegant method for modeling novel or unseen objects, utilizing established appearance cues and accounting for inherent uncertainties.
KIX: A Knowledge and Interaction-Centric Metacognitive Framework for Task Generalization
People aptly exhibit general intelligence behaviors in solving a variety of tasks with flexibility and ability to adapt to novel situations by reusing and applying high-level knowledge acquired over time.
Saturn: Efficient Multi-Large-Model Deep Learning
In this paper, we propose Saturn, a new data system to improve the efficiency of multi-large-model training (e. g., during model selection/hyperparameter optimization).
Saturn: An Optimized Data System for Large Model Deep Learning Workloads
Such models need multiple GPUs due to both their size and computational load, driving the development of a bevy of "model parallelism" techniques & tools.
Objects as Spatio-Temporal 2.5D points
Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to accomplish that is extremely challenging to procure.
Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages
Cross-lingual dubbing of lecture videos requires the transcription of the original audio, correction and removal of disfluencies, domain term discovery, text-to-text translation into the target language, chunking of text using target language rhythm, text-to-speech synthesis followed by isochronous lipsyncing to the original video.
Hydra: A System for Large Multi-Model Deep Learning
In this paper, we present Hydra, a system designed to tackle such challenges by enabling out-of-the-box scaling for multi-large-model DL workloads on even commodity GPUs in a resource-efficient manner.
Ranked #5 on
Language Modelling
on WikiText-2
(using extra training data)
A novel method of fuzzy time series forecasting based on interval index number and membership value using support vector machine
There are generally, four factors that determine the performance of the forecasting method (1) number of intervals (NOIs) and length of intervals to partition universe of discourse (UOD) (2) fuzzification rules or feature representation of crisp time series (3) method of establishing fuzzy logic rule (FLRs) between input and target values (4) defuzzification rule to get crisp forecasted value.
Morphological Segmentation Inside-Out
Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output.
Predicting Eating Events in Free Living Individuals -- A Technical Report
For predicting food purchasing events, the RBF-SVM model (0. 7395) outperforms others.
MLSys: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Belief dynamics extraction
Estimating the structure of these internal states is crucial for understanding the neural basis of behavior.
Document Structure Measure for Hypernym discovery
Hypernym discovery is the problem of finding terms that have is-a relationship with a given term.
Fine Grained Classification of Personal Data Entities
Entity Type Classification can be defined as the task of assigning category labels to entity mentions in documents.
Deep Domain Adaptation under Deep Label Scarcity
The goal behind Domain Adaptation (DA) is to leverage the labeled examples from a source domain so as to infer an accurate model in a target domain where labels are not available or in scarce at the best.
Bipedal Walking Robot using Deep Deterministic Policy Gradient
The control systems community has started to show interest towards several machine learning algorithms from the sub-domains such as supervised learning, imitation learning and reinforcement learning to achieve autonomous control and intelligent decision making.
Model-based Pricing for Machine Learning in a Data Marketplace
Finally, we conduct extensive experiments, which validate that the MBP framework can provide high revenue to the seller, high affordability to the buyer, and also operate on low runtime cost.
In-RDBMS Hardware Acceleration of Advanced Analytics
The data revolution is fueled by advances in machine learning, databases, and hardware design.
Dialogue Act Sequence Labeling using Hierarchical encoder with CRF
Dialogue Act recognition associate dialogue acts (i. e., semantic labels) to utterances in a conversation.
Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers?
Our results show that these high-capacity classifiers are surprisingly and counter-intuitively more robust to avoiding KFK joins compared to linear classifiers, refuting an intuition from the prior work's analysis.
Morphological Analysis of the Dravidian Language Family
The Dravidian languages are one of the most widely spoken language families in the world, yet there are very few annotated resources available to NLP researchers.
Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent
We fill this crucial research gap by proposing a new lossless compression scheme we call tuple-oriented compression (TOC) that is inspired by an unlikely source, the string/text compression scheme Lempel-Ziv-Welch, but tailored to MGD in a way that preserves tuple boundaries within mini-batches.
Novelty Learning via Collaborative Proximity Filtering
We meet these challenges by developing a model of novelty preferences that learns and tracks latent user tastes.
Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address \emph{both} issues in an integrated manner.
