Microsoft Research ブログ
読み込み中…

Microsoft Research ブログ
Factorized layers revisited: Compressing deep networks without playing the lottery
| Misha Khodak, Neil Tenenholtz, Lester Mackey, と Nicolo Fusi
From BiT (928 million parameters (opens in new tab)) to GPT-3 (175 billion parameters (opens in new tab)), state-of-the-art machine learning models are rapidly growing in size. With the greater expressivity and easier trainability of these models come skyrocketing training…

Microsoft Research ブログ
Research at Microsoft 2020: Addressing the present while looking to the future
Microsoft researchers pursue the big questions about what the world will be like in the future and the role technology will play. Not only do they take on the responsibility of exploring the long-term vision of their research, but they…