Deep Learning

@DeepLearning18

Deep Learning - Life School

於六月 2019 加入

10貼文 139位跟隨者 13個跟隨中

你可能會喜歡

@Club2030Afrique

@pbpilatre

@URPSCDNA

@MCResearchInst

@fmchevalier

@GuillaumeLabbez

@maestro2balzak

@chantal_edouard

@evinhas

@frededlens

Deep Learning 已轉發

Andrew Ng

@AndrewYNg

2023年11月29日

New short course on sophisticated RAG (Retrieval Augmented Generation) techniques is out! Taught by @jerryjliu0 and @datta_cs of @llama_index and @truera_ai , this teaches advanced techniques that help your LLM generate good answers. Topics include: - Sentence-window retrieval,…

Deep Learning 已轉發

David Mimno

@dmimno

2022年6月17日

The Text as Data Conference (TADA) 2022 will be happening at Cornell Tech on beautiful Roosevelt Island in NYC Oct 6-7. Abstract submissions are due July 18. Please RT!

dmimno's tweet image. The Text as Data Conference (TADA) 2022 will be happening at Cornell Tech on beautiful Roosevelt Island in NYC Oct 6-7. Abstract submissions are due July 18. Please RT!

Deep Learning 已轉發

Dan Jurafsky

@jurafsky

2021年12月30日

Here's the December 2021 release of draft chapters for Speech and Language Processing, just in time for Jim and I to wish you all a Happy New Year! Enjoy! web.stanford.edu/~jurafsky/slp3/

Deep Learning 已轉發

Basil Mustafa

@_basilM

2022年6月7日

Beep beep! Introducing LIMoE, the Language Image Mixture of Experts: a single model, processing both modalities for contrastive image-text modelling. Cruises straight to 84.1% 0shot ImageNet accuracy without any modality-specific architectures or pre-training. (1/10)

_basilM's tweet image. Beep beep! Introducing LIMoE, the Language Image Mixture of Experts: a single model, processing both modalities for contrastive image-text modelling. Cruises straight to 84.1% 0shot ImageNet accuracy without any modality-specific architectures or pre-training. (1/10)

Deep Learning 已轉發

rohan anil

@_arohan_

2022年9月14日

Just remembered again how true this with learning the LR literature, there is so much compute spend in finding meta-hyper-parameters (that’s hidden away) that results look great in paper but fails on new problem.

Ben Poole

@poolio

2022年9月13日

"We present a hyperparameter-free method..." def beautiful_method(): return method(lr=3e-4, alpha=0.13, gamma=pi/9.1)

Deep Learning 已轉發

Darek Kłeczek

@dk21

2022年9月15日

How train the best performing NLP model? 3 techniques to experiment with. 🧵

Deep Learning 已轉發

Stanford NLP Group

@stanfordnlp

2022年9月15日

The SERAC model for small edits to large neural networks by @_eric_mitchell_ Charles Lin @ABosselut @chrmanning @chelseabfinn is the bottom item in @DeepLearningAI_’s The Batch this week. We’re not sure why this week—it must be a slow AI news week. 😭 deeplearning.ai/the-batch/issu…