Search Results for author:
Found 15 papers, 1 papers with code
IBM Deep Learning Service
Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision.
Distributed, Parallel, and Cluster Computing
Improving Transferability of Deep Neural Networks
This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset.
P2L: Predicting Transfer Learning for Images and Semantic Relations
We use this measure, which we call "Predict To Learn" ("P2L"), in the two very different domains of images and semantic relations, where it predicts, from a set of "source" models, the one model most likely to produce effective transfer for training a given "target" model.
NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
The typical way of conducting large scale NAS is to search for an architectural building block on a small dataset (either using a proxy set from the large dataset or a completely different small scale dataset) and then transfer the block to a larger dataset.
Large Scale Neural Architecture Search with Polyharmonic Splines
Neural Architecture Search (NAS) is a powerful tool to automatically design deep neural networks for many tasks, including image classification.
Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment
We propose a new word representation method derived from visual objects in associated images to tackle the lexical entailment task.
Predictive Model Selection for Transfer Learning in Sequence Labeling Tasks
Transfer learning is a popular technique to learn a task using less training data and fewer compute resources.
Automatic Labeling of Data for Transfer Learning
Transfer learning uses trained weights from a source model as the initial weightsfor the training of a target dataset.
G2L: A Geometric Approach for Generating Pseudo-labels that Improve Transfer Learning
Transfer learning is a deep-learning technique that ameliorates the problem of learning when human-annotated labels are expensive and limited.
Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models
In each episode of the search process, a NAS controller predicts a reward based on the distillation loss and latency of inference.
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models
Our target of study includes Output Distribution (OD) transfer, Hidden State (HS) transfer with various layer mapping strategies, and Multi-Head Attention (MHA) transfer based on MiniLMv2.
Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings
This leads to an improved language model for analyzing spoken transcripts while avoiding an audio processing overhead at test time.
Muted: Multilingual Targeted Offensive Speech Identification and Visualization
Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web.
Efficient Models for the Detection of Hate, Abuse and Profanity
This is unacceptable in civil discourse. The detection of Hate, Abuse and Profanity in text is a vital component of creating civil and unbiased LLMs, which is needed not only for English, but for all languages.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
