DLeX: AI Python

Forwarded from AI, Python, Cognitive Neuroscience (Farzad)

Deep Learning:
http://course.fast.ai
NLP:
http://bit.ly/fastai-nlp
Comp Linear Algebra:
http://github.com/fastai/numerical-linear-algebra
Bias, Ethics, & AI:
http://fast.ai/topics/#ai-in-society
Debunk Pipeline Myth:
http://bit.ly/not-pipeline
AI Needs You:
http://bit.ly/rachel-TEDx
Ethics Center:
http://bit.ly/USF-CADE

❇️ @AI_Python_EN

www.fast.ai

new fast.ai course: A Code-First Introduction to Natural Language Processing

fast.ai's newest course is Code-First Intro to NLP. It covers a blend of traditional NLP techniques, recent deep learning approaches, and urgent ethical issues.

393 viewsFarzad, 12:09

DLeX: AI Python

Forwarded from AI, Python, Cognitive Neuroscience (Farzad)

Simple, Scalable Adaptation for Neural Machine Translation

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. Researchers from Google propose a simple yet efficient approach for adaptation in #NMT. Their proposed approach consists of injecting tiny task specific adapter layers into a pre-trained model. These lightweight adapters, with just a small fraction of the original model size, adapt the model to multiple individual tasks simultaneously.

Guess it can be applied not only in #NMT but in many other #NLP, #NLU and #NLG tasks.

Paper: https://arxiv.org/pdf/1909.08478.pdf

#BERT

❇️ @AI_Python_EN

196 viewsFarzad, 13:25

DLeX: AI Python

مهم‌ترین کتابخانه های علم داده در #پایتون

این نمودار از بررسی سایت Github تهیه و توسط سایت ActiveWizards منتشر شده است.

@ai_python

4.92K viewsMilad Farzalizadeh, edited 13:40

DLeX: AI Python

Convolutional #NeuralNetworks have become a foundational network architecture for numerous deep learning-based #ComputerVision tasks. Here, Heartbeat contributor Brian Mwangi explores their evolution in this excellent review of the research.
https://bit.ly/32fkz0p

Medium

A Research Guide to Convolution Neural Networks

Examining the advancements of CNN architectures over the past few years

4.96K viewsFa, 09:00

DLeX: AI Python

Bayesian Optimization Meets Riemannian Manifolds in Robot Learning

Jaquier et al.: https://lnkd.in/gEv2b5g

#BayesianOptimization #Robotics
#MachineLearning

5.1K viewsFa, 09:01

DLeX: AI Python

Slides https://t.co/X5gKgF11bE New optimization: competitive gradient descent (CGD) for training GAN/multi-agent systems. Implicit competitive regularization from CGD means that we get SOTA with no explicit gradient penalty, better stability and no mode collapse
#AI #DeepLearning

❇️ @AI_Python
✴️ @AI_Python_EN

4.82K viewsFa, 12:15

DLeX: AI Python

A new antibody search engine with publication data. #Free online platform for academic scientists!
#openaccess #openscience #phdchat

https://landing.benchsci.com/

4.39K viewsFa, 08:50

DLeX: AI Python

Uncertainty Quantification in Deep Learning

https://www.inovex.de/blog/uncertainty-quantification-deep-learning/

5.18K viewsFa, 08:51

DLeX: AI Python

Transformers working for RL! Two simple modifications: move layer-norm and add gating creates GTrXL: an incredibly stable and effective architecture for integrating experience through time in RL.
https://arxiv.org/abs/1910.06764

❇️ @AI_Python
✴️ @AI_Python_EN

5.72K viewsFa, edited 08:53

DLeX: AI Python

Transformers working for RL! Two simple modifications: move layer-norm and add gating creates GTrXL: an incredibly stable and effective architecture for integrating experience through time in RL. https://arxiv.org/abs/1910.06764 ❇️ @AI_Python ✴️ @AI_Python_EN

By using GTrXL we find large performance gains in reinforcement learning tasks requiring memory and integration of experience through time compared to LSTM, whilst not compromising on more reactive RL tasks.
This architecture really shines on some continuous control tasks requiring long temporal memory horizons, and compared to previous work doesn't require any auxiliary losses.

4.24K viewsFa, 09:12

DLeX: AI Python

35 پروژه علم داده

#منابع #علم_داده #آموزش
#DataScience

💠 Link

❇️ @AI_Python
✴️ @AI_Python_EN

9.68K viewsFa, 13:58

DLeX: AI Python

Forwarded from دستاوردهای یادگیری عمیق(InTec)

تمام تغییرات مهم شبکه‌های کانولوشن تا ۲۰۱۸ :

Paper link

157 viewsFarzad, 11:18

DLeX: AI Python

راه فراگیری علم داده برای مبتدیان

#منابع #علم_داده #آموزش
#DataScience

❇️ @AI_Python
✴️ @AI_Python_EN

4.95K viewsFarzad, 17:46

DLeX: AI Python

مقاله داغ
Detect Online Trolls in Elections

https://arxiv.org/abs/1910.07130
#هوش_مصنوعی #منابع #داده_کاوی #مقاله
#AI #ArtificialIntelligence #datamining

❇️ @AI_Python
✴️ @AI_Python_EN

4.85K viewsFarzad, edited 18:55

DLeX: AI Python

Forwarded from دستاوردهای یادگیری عمیق(InTec)

Training Data

این سایت هم دیتاست‌های مناسب رو یکجا جمع‌آوری کرده و در دسترس قرار داده و هم کمک می‌کنه از همون مدل‌های اولیه برای لیبل زدن دیتاهای بیشتر استفاده کنید.

150 viewsFarzad, 07:18

DLeX: AI Python

Forwarded from Data Experts (javad vhd)

2:47

This media is not supported in your browser

VIEW IN TELEGRAM

سخنرانی ارتور بنجامین
در مورد اینکه افراد رو در چه حوزه ای باید تربیت کرد!
ریاضیات یا احتمالات !!

@Data_Experts

114 viewsFarzad, 08:23

DLeX: AI Python

Forwarded from بایگانی تبلیغات ۹۸,۹۹

🔷داده یکی از ارزشمندترین و مهم ترین سرمایه های سازمان ها و کسب و کارها می باشد و برای نگهداری و تولید این سرمایه فرصت های شغلی بسیاری وجود دارد که راه رسیدن به ثروت را برای متخصصان این حوزه هموار می سازد اگر شما هم علاقه مند به متخصص شدن در این حوزه هستید با ما تماس بگیرید

☎️مشاوره وثبت نام
۶۶۰۷۵۶۴۱-۶۶۰۷۵۶۲۶
جزئیات دوره تربیت دانشمند داده ↙️
http://bit.ly/2pwzWmp
جزئیات دوره تربیت مهندس داده↙️
http://bit.ly/2Mys1NB

🔷با کانال تلگرام ما همراه باشید↙️

https://t.me/joinchat/AAAAAD6fyUw0AYXKLGbkow
🌐www.SCTAE.info

142 viewsA Vafa, 13:57

DLeX: AI Python

Forwarded from DLeX: AI Python (Deleted Account)