How to Reduce the Variance of Deep Learning Models in Keras Using Model Averaging Ensembles

#deeplearning #machinelearning

https://bit.ly/2PQlEVu


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

#Statistics don't lie, but statisticians may
Data Science isn't tough, but Data Scientists should be.

#datascience #aspirants tell me the hurdles you are facing every day in your transition. I would like to hear out. I have a lot of friends in my network who can answer. Even I will.

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Amazing. Train a network to classify papers (accept/reject). Then run the network on the paper describing the network, and it classifies the paper as a strong reject. This is why we can't have nice paper classifiers.

https://arxiv.org/abs/1812.08775


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Names for collections of code in various languages:

A pile of JavaScript

A crystal of Haskell

An undefinedness of C++

A liability of Python

A French grad student of OCaml

An ambition of Rust

A bank of COBOL

A postmodernism of Perl

An accident of C

A Unabomber of Forth

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

9,216 IBM Power9 CPUs and 27,648 Nvidia Volta GPUs #Supercomputer performs 200 quadrillion calculations per second, #USA tops #China for the world's fastest #computer #AI #DataScience #DataAnalytics #IoT #BigData

http://bit.ly/2sSORWi

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

The FEYNMAN technique of learning:

STEP 1 - Pick and study a topic

STEP 2 - Explain the topic to someone, like a child, who is unfamiliar with the topic

STEP 3 - Identify any gaps in your understanding

STEP 4 - Review and Simplify!

- Richard Feynman

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

An Amoeba-Based Computer Calculated Approximate Solutions to a Very Hard Math Problem

Article by Daniel Oberhaus: https://lnkd.in/eHJRTBS

#biocomputers


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

The Unreasonable Effectiveness of Recurrent Neural Networks

Blog (2015) by Andrej Karpathy: https://lnkd.in/eNC7BK5

#DeepLearning #NeuralNetworks #RecurrentNeuralNetworks #RNN


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Can Neural Networks Remember?

Slides by Vishal Gupta: https://lnkd.in/e_EUYGv

#RecurrentNeuralNetworks #LongShortTermMemory #LSTM #neuralnetworks


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Understanding LSTM Networks

By Christopher Olah: https://lnkd.in/eWJkwp3

#DeepLearning #LSTM #RecurrentNeuralNetworks


❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Best of arXiv.org for AI, Machine Learning, and Deep Learning

🔸 November 2018

🔸 November 2017

🔸 July 2018

🔸 April 2018

🔸 June 2018

🔸 September 2018

🔸 October 2018

🔸 August 2018

#DeepLearning #machinelearning #AI #Artificialinteligence #مقاله

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Wanna see progress of a long running operation easily in your Jupyter notebook? Use the wonderful tqdm module - https://github.com/tqdm/tqdm#ipython-jupyter-integration …. As a bonus, the name is Arabic & Spanish inspired! twitter JupyterProject
Mona Jalal Siad: tqdm stems from تقدم which means "progress"
#python

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Eirikur Agustsson Research Scientist Google

this paper on how to properly interpolate samples from GANs and VAEs has been accepted to ICLR 2019!

Paper: Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models (
https://openreview.net/forum?id=BklCusRct7&noteId=BklCusRct7)
TLDR: Stop using linear interpolation!

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

When ML has no common sense 😂
#ML #MachineLearning

❇️ @AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN

Could you also consider taking a look at "fastprogress", our recent replacement for tqdm, which has some nice extra features (see the readme) and avoids
some of tqdm's bugs:

https://t.co/QflMyWcUTE


✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

👉 If you like our channel, i invite you to share it with your friends:
Our channel in english: ✴️ @AI_Python_EN
Our Daily arXiv Channel: 🗣 @AI_Python_Arxiv

BTW: Thank you for joining :)

Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
Article
Code
Online Demo
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

ProjectJupyter⁩ notebook server running on home_assistant⁩ Hassio on an ⁦#Raspberry_Pi⁩ viewed in the iOS app on my Apple⁩ iPhone, what a time to be alive

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Based on 2018 HackerRank's Developer survey, #Javascript #Java #Python stand out as the top 3 expected Programming languages but what's next is more important. That's being Language Agnostic!

This is very important especially in #DataScience and #MachineLearning where we always put R vs Python, but with market expecting Language Agnostic Developers, It's good to have both the languages at your disposal.

The screenshot is from a Gender-focused #Kaggle Kernel I did sometime back : https://lnkd.in/fXCDHjv

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

AndrewYNg from LandingAI sharing his thoughts around #AI & #MachineLearning.

https://www.swarmapp.com/c/kLTdYT7cXAO

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

"Godel Machines, Meta-Learning, and LSTMs" - interview with Juergen Schmidhuber

Juergen Schmidhuber is the co-creator of long short-term memory networks (LSTMs) which are used in billions of devices today for speech recognition, translation, and much more. Over 30 years, he has proposed a lot of interesting, out-of-the-box ideas in artificial intelligence including a formal theory of creativity. This conversation is part of the Artificial Intelligence podcast and the MIT course 6.S099: Artificial General Intelligence. The conversation and lectures are free and open to everyone

#MachineLearning #AI

https://youtu.be/3FIo6evmweo

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv