User profiles for I. Narang
Indra NarangProfessor of Paediatrics, Temerty Faculty of Medicine, University of Toronto Verified email at sickkids.ca Cited by 4746 |
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional
data naturally reside on the vertices of weighted graphs. The emerging field of …
data naturally reside on the vertices of weighted graphs. The emerging field of …
Obstructive sleep disordered breathing in 2-to 18-year-old children: diagnosis and management
This document summarises the conclusions of a European Respiratory Society Task Force
on the diagnosis and management of obstructive sleep disordered breathing (SDB) in …
on the diagnosis and management of obstructive sleep disordered breathing (SDB) in …
The complexity of mitogen-activated protein kinases (MAPKs) made simple
M Krishna, H Narang - Cellular and Molecular Life Sciences, 2008 - Springer
The mitogen-activated protein kinase (MAPK) pathways are known to be involved in various
processes of growth, differentiation and cell death. In spite of their ubiquitous presence and …
processes of growth, differentiation and cell death. In spite of their ubiquitous presence and …
[HTML][HTML] Deep speech 2: End-to-end speech recognition in english and mandarin
…, Y Liu, W Li, X Li, D Ma, S Narang… - International …, 2016 - proceedings.mlr.press
We show that an end-to-end deep learning approach can be used to recognize either English
or Mandarin Chinese speech–two vastly different languages. Because it replaces entire …
or Mandarin Chinese speech–two vastly different languages. Because it replaces entire …
Palm: Scaling language modeling with pathways
Large language models have been shown to achieve remarkable performance across a variety
of natural language tasks using few-shot learning, which drastically reduces the number …
of natural language tasks using few-shot learning, which drastically reduces the number …
Exploring the limits of transfer learning with a unified text-to-text transformer
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned
on a downstream task, has emerged as a powerful technique in natural language …
on a downstream task, has emerged as a powerful technique in natural language …
Scaling instruction-finetuned language models
Finetuning language models on a collection of datasets phrased as instructions has been
shown to improve model performance and generalization to unseen tasks. In this paper we …
shown to improve model performance and generalization to unseen tasks. In this paper we …
Llama 2: Open foundation and fine-tuned chat models
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large
language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-…
language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-…
[HTML][HTML] Integration of external signaling pathways with the core transcriptional network in embryonic stem cells
Transcription factors (TFs) and their specific interactions with targets are crucial for specifying
gene-expression programs. To gain insights into the transcriptional regulatory networks in …
gene-expression programs. To gain insights into the transcriptional regulatory networks in …
Myotonic dystrophy mutation: an unstable CTG repeat in the 3′ untranslated region of the gene
…, G Shutler, C Amemiya, G Jansen, C Neville, M Narang… - Science, 1992 - science.org
Myotonic dystrophy (DM) is the most common inherited neuromuscular disease in adults,
with a global incidence of 1 in 8000 individuals. DM is an autosomal dominant, multisystemic …
with a global incidence of 1 in 8000 individuals. DM is an autosomal dominant, multisystemic …