AlexaTM 20B is Amazon’s New Language Super Model Which is Also Capable of Few-Shot Learning

The model is the largest seq2seq architecture capable of few-shot-learning.

Source: https://www.iqvis.com/blog/amazon-reorganized-ai-and-machine-learning/

I recently started an AI-focused educational newsletter, that already has over 125,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Please give it a try by subscribing below:

TheSequence

In the last few years, the progress in natural language understanding(NLU) really challenges human imagination. Some of the milestones achieved by models like OpenAI GPT-3 seem unimaginable just a few years ago. Large AI labs like Microsoft Research, Google Brain, Alexa AI, DeepMind or Meta AI are regularly pushing the boundaries of NLU research. One of the latest entrances in the language supermodel category came from Amazon’s Alexa AI labs with Alexa Teacher Models™ 20B, a large seq2seq model that set up new marks in few-shot learning.