hardest: features and parameters of the model, most expensive: data collection, cleaning and labeling, most time consuming: multiple iterations in order to converge to the optimal parameters, testing & evaluation.

Dr François Chollet

This is a great answer and I agree -- modelling/science is the hardest (if you want to do it right), and also the most time-consuming due to lengthy iterations. Meanwhile data collection and labelling is the most expensive, and often the most important to the success of a project.

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

"A Brief Introduction to Machine Learning for Engineers"

By Osvaldo Simeone: https://lnkd.in/eT9FVYd

#ArtificialIntelligence #MachineLearning #NeuralNetworks


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

A Full Hardware Guide to Deep Learning

By Tim Dettmers: https://lnkd.in/emiGW6p

#ai #deeplearning #gpu #gpus #hardware


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Playing first-person shooter games with webcam and #DeepLearning (Tensorflow #ObjectDetection)

Find out how you can use an object detection model to control and play any first-person shooter game with your computer's webcam. Links to the code below.

Full Video: https://lnkd.in/eBq7z4r

Blog: https://lnkd.in/eekrqWk

Code: https://lnkd.in/ekhwwiJ

Subscribe: youtube.com/c/DeepGamingAI

@AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN

Want to learn ML through code examples?

Check out these 5 scikit-learn tutorials to get started:

1. Randomized search vs grid search - https://lnkd.in/gjHpjJK

2. Using regularization to improve your GBM models - https://lnkd.in/gYNCNGD

3. Selecting the correct number of estimators for GBM models - https://lnkd.in/gW5AQTk

4. Selecting the correct number of estimators for random forest models - https://lnkd.in/ge66wUH

5. Decision boundary comparison for popular classifier models (check out this viz!) - https://lnkd.in/gHVg9nm

There are a ton more that you can go through on the sk-learn tutorial page as well.

👉 Check them out here - https://lnkd.in/gAv3hq7

👉 If you need more help learning machine learning or getting a job as a data scientist, then hop on my email list and I'd be happy to help - https://lnkd.in/g7AYg72

#datascience #machinelearning

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

A simple notebook to remove the background of objects using Mask R-CNN

By Zaid Alyafeai: https://lnkd.in/exr7yWi

#artificialinteligence #deeplearning #machinelearning #tensorflow

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

Ten Simple Rules for Reproducible Research in Jupyter Notebooks

Rule et al.: https://lnkd.in/efWmkyi

#BigData #ComputerScience #DataScience #MachineLearning

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Tuning Machine Learning Hyperparameters

https://heartbeat.fritz.ai/tuning-machine-learning-hyperparameters-40265a35c9b8

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

if you're going to start a #ML services startup, make it about data collection and labelling. This is main pain point, and where the most value can be unlocked.

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

A Concise Handbook of TensorFlow (https://tf.wiki ) Online book for those who already knows #ML / #DL theories and want to focus on learning #TensorFlow itself

https://tf.wiki/en/preface.html

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

The International Conference on #Probabilistic Programming Talks from the #PROBPROG 2018 #Conference, held at the MIT Media Lab in Cambridge

https://www.youtube.com/playlist?list=PL_PW0E_Tf2qvXBEpl10Y39RULTN-ExzZQ



❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

rlkit – Reinforcement learning framework and algorithms implemented in #PyTorch

https://github.com/vitchyr/rlkit

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

videos of #NeurIPS2018 invited talks: https://videos.videoken.com/index.php/videoscategory/neurips-2018/ … videos of more sessions here: https://www.facebook.com/pg/nipsfoundation/videos

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

How to Clone a Partition or Hard drive in #Linux https://www.tecmint.com/clone-linux-partitions/

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Interested in research on the interface of #evolution, systems and molecular #biology, #mathematics, and #statistics? Apply now to join the Evolutionary Dynamics lab IGCiencia as a postdoc, programmer, or PhD student! https://evoldynamics.org/positions Please spread the word!

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

share white paper on Dopamine, #RL framework. got lots of positive feedback at #NeurIPS2018 ,

https://arxiv.org/abs/1812.06110 https://github.com/google/dopamine

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

#Programming
👇 It is a painful thing, to look at your own trouble and know that you yourself and no one else has made it. ~Sophocles Debugging #software includes:
👉Control flow analysis
👉Unit | integration testing
👉Log file analysis
👉Monitoring
👉Memory dumps
👉Profiling

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

3 reasons why #Coding (specifically, #Python) Should Become Your Official Corporate Language:

1)Teaches to think and solve problems.

2)Teaches the principles of Open-Source.

3)Teaches to work collaboratively.

https://bit.ly/2z3Qp2A #abdsc #DataScience #DataScientists
❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

Copying an element from a photo and pasting it into a painting. Main idea is a modification of the VGG style transfer technique. Fun results.

Paper:
https://arxiv.org/pdf/1804.03189v3.pdf
Code:
https://github.com/luanfujun/deep-painterly-harmonization

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

The Netflix Data War

https://simplystatistics.org/2018/12/19/the-netflix-data-war/

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python

The Relationship Between #MachineLearning and #AI

- Machine Learning exists without AI
- AI exists without Machine Learning
- New AI embeds Machine Learning
- Machine Learning rarely uses AI You

got all that? 🤓

❇️ @AI_Python_EN
🗣 @AI_Python_arXiv
✴️ @AI_Python