Building Neural Network Models That Can Reason

Автор: Microsoft Research

Загружено: 2019-07-30

Просмотров: 29638

Описание: Deep learning has had enormous success on perceptual tasks but still struggles in providing a model for inference. To address this gap, we have been developing networks that support memory, attention, composition, and reasoning. Our MACnet and NSM designs provide a strong prior for explicitly iterative reasoning, enabling them to learn explainable, structured reasoning, as well as achieve good generalization from a modest amount of data. The Neural State Machine (NSM) design also emphasizes the use of a more symbolic form of internal computation, represented as attention over symbols, which have distributed representations. Such designs impose structural priors on the operation of networks and encourage certain kinds of modularity and generalization. We demonstrate the models’ strength, robustness, and data efficiency on the CLEVR dataset for visual reasoning (Johnson et al. 2016), VQA-CP, which emphasizes disentanglement (Agrawal et al. 2018), and our own GQA (Hudson and Manning 2019). Joint work with Drew Hudson.

See more at https://www.microsoft.com/en-us/resea...

Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...

Building Neural Network Models That Can Reason

Доступные форматы для скачивания:

Скачать видео

Информация по загрузке:

Скачать аудио

Похожие видео

Efficient Robot Skill Learning: Grounded Simulation Learning and Imitation Learning from Observation

Efficient Robot Skill Learning: Grounded Simulation Learning and Imitation Learning from Observation

Christopher D Manning: A Neural Network Model That Can Reason (ICLR 2018 invited talk)

Christopher D Manning: A Neural Network Model That Can Reason (ICLR 2018 invited talk)

From Deep Learning of Disentangled Representations to Higher-level Cognition

From Deep Learning of Disentangled Representations to Higher-level Cognition

Automated Reasoning Basics | Douglas Lenat and Lex Fridman

Automated Reasoning Basics | Douglas Lenat and Lex Fridman

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

The Thousand Brains Theory

The Thousand Brains Theory

Пожалуй, главное заблуждение об электричестве [Veritasium]

Пожалуй, главное заблуждение об электричестве [Veritasium]

LSTM is dead. Long Live Transformers!

LSTM is dead. Long Live Transformers!

Quantum Computing for Computer Scientists

Quantum Computing for Computer Scientists

Как сжимаются изображения? [46 МБ ↘↘ 4,07 МБ] JPEG в деталях

Как сжимаются изображения? [46 МБ ↘↘ 4,07 МБ] JPEG в деталях

Machine Learning Zero to Hero (Google I/O'19)

Machine Learning Zero to Hero (Google I/O'19)

MIT AGI: Building machines that see, learn, and think like people (Josh Tenenbaum)

MIT AGI: Building machines that see, learn, and think like people (Josh Tenenbaum)

49 минут, которые ИЗМЕНЯТ ваше понимание Вселенной | Владимир Сурдин

49 минут, которые ИЗМЕНЯТ ваше понимание Вселенной | Владимир Сурдин

11. Introduction to Machine Learning

11. Introduction to Machine Learning

A Neural Network Model That Can Reason - Prof. Christopher Manning

A Neural Network Model That Can Reason - Prof. Christopher Manning

Обучение крупномасштабных видеомоделей | Дилара Гёкай, Google DeepMind | BLISS e.V.

Обучение крупномасштабных видеомоделей | Дилара Гёкай, Google DeepMind | BLISS e.V.

Stanford Seminar - Information Theory of Deep Learning, Naftali Tishby

Stanford Seminar - Information Theory of Deep Learning, Naftali Tishby

Краткое объяснение больших языковых моделей

Краткое объяснение больших языковых моделей

Yoshua Bengio: From System 1 Deep Learning to System 2 Deep Learning (NeurIPS 2019)

Yoshua Bengio: From System 1 Deep Learning to System 2 Deep Learning (NeurIPS 2019)

MIT 6.S191 (2020): Neurosymbolic AI

MIT 6.S191 (2020): Neurosymbolic AI