Wednesday, November 6, 2024

Artificial Intelligence news

How ChatGPT search paves...

This story originally appeared in The Algorithm, our weekly newsletter on AI....

This AI-generated Minecraft may...

When you walk around in a version of the video game Minecraft...

OpenAI brings a new...

ChatGPT can now search the web for up-to-date answers to a user’s...

Chasing AI’s value in...

Inspired by an unprecedented opportunity, the life sciences sector has gone all...
HomeMachine LearningNeural Transducer Training:...

Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation



The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the capacity of state-of-the-art GPUs, limiting batch size and sequence lengths. In this work, we analyze the time and space complexity of a typical transducer training setup. We propose a memory-efficient training method that computes the transducer loss and gradients sample by sample. We present optimizations to increase the efficiency and parallelism of the…



Article Source link and Credit

Continue reading

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In...

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models

The rapid evolution of Large Language Models (LLMs) and conversational assistants necessitates dynamic, scalable, and configurable conversational datasets for training and evaluation. These datasets must accommodate diverse user interaction modes, including text and voice, each presenting unique modeling...

Promoting Cross-Modal Representations to Improve Multimodal Foundation Models for Physiological Signals

Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining foundation models is a promising avenue for success. However,...