Reducing the Need for Labeled Data in Generative Adversarial Networks #DataScience #MachineLearning #ArtificialIntelligence

http://bit.ly/2FqeJiF

✴️ @AI_Python_EN

A PyTorch implementation of BigGAN with pretrained weights and conversion scripts

By Thomas Wolf: https://lnkd.in/e_Pph_T

#pytorch #biggan #computervision #artificialintelligence
#generativeadversarialnetwork

✴️ @AI_Python_EN

Interpretable machine learning is so important doesn’t matter whether you want to understand a simple linear regression model to more complex ones like neural networks. Understanding your models help to prevent biases, gain trust and help you building better models. If you haven’t done it yet then start with it now! It’s never too late! #deeplearning #machinelearning #explainableAI

✴️ @AI_Python_EN

I find Mark Berliner’s Bayesian Hierarchical Model (BHM) paradigm helpful.

At the top level is the data model, which is a probability model that specifies the distribution of the data given an underlying “true” process (sometimes called the hidden or latent process) and given some parameters that are needed to specify this distribution.

At the next level is the process model, which is a probability model that describes the hidden process (and, thus, its uncertainty) given some parameters. Note that at this level the model does not need to account for measurement uncertainty. The process model can then use science-based theoretical or empirical knowledge, which is often physical or mechanistic.

At the bottom level is the parameter model, where uncertainty about the parameters is modeled. From top to bottom, the levels of a BHM are:

1. Data model: [data|process, parameters]
2. Process model: [process|parameters]
3. Parameter model: [parameters]

Each of these levels could have sub-levels, for which conditional-probability models could be given. Ultimately, we are interested in the posterior distribution:

[process, parameters|data] ∝ [data|process, parameters] ×[process|parameters] ×[parameters]

Excerpted from Spatio-Temporal Statistics with R (Wikle et al.)

✴️ @AI_Python_EN

Everyone strives to build accurate and high-performing #datascience models. Check out these articles that list down the different ways to improve your model's accuracy and evaluate it:

8 Proven Ways for improving the “Accuracy” of a #MachineLearning Model - https://buff.ly/2TP4sGI

Improve Your Model Performance using Cross Validation (in Python and R) - https://buff.ly/2HGNV05

7 Important Model Evaluation Error Metrics Everyone should know - https://buff.ly/2HsYgxm

✴️ @AI_Python_EN

Excellent new GAN contribution from Berkeley, NVIDIA and MIT: Semantic Image Synthesis with Spatially-Adaptive Normalization (SPADE). Do checkout images and videos, it really is good.

"We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal because the normalization layers tend to wash away semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method compared to existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows users to easily control the style and content of synthesis results as well as create multi-modal results."

website: https://lnkd.in/fhi8Fmq
paper: https://lnkd.in/fv8HCGn
github (code coming soon): https://lnkd.in/fwPnMxv

#gan #deeplearning #artificialintelligence

✴️ @AI_Python_EN

To much spelling error in your dataset?


Peter Norvig (Research Director at Google, previously director of search quality) revolutionize search engine quality by giving power to reduce spelling error (by splits, deletes, transposes, replaces, and inserts). You can see the comprehensive guide (with python code) at his website https://lnkd.in/fEb3v2a

#python #datasets #codes #statistician

✴️ @AI_Python_EN

Ranking Tweets with TensorFlow

Blog by Yi Zhuang, Arvind Thiagarajan, and Tim Sweeney: https://lnkd.in/eiNseET

#MachineLearning #TensorFlow #Twitter

✴️ @AI_Python_EN

The evolution of art through the lens of deep convolutional networks

“The Shape of Art History in the Eyes of the Machine”, Elgammal et al.: https://lnkd.in/dgjmqYc

#art #artificialintelligence #deeplearning

✴️ @AI_Python_EN

Training my model
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

This is a fun application of the superres method from fastdotai lesson 7 - turning line drawings into shaded pictures! https://forums.fast.ai/t/share-your-work-here/27676/1204

✴️ @AI_Python_EN

Check out new blog post on Coconet 🥥, the #ml behind the Bach Doodle that’s live now! It’s a flexible infilling model that generates counterpoint through rewriting. http://g.co/magenta/coconet

✴️ @AI_Python_EN

PhD thesis Neural Transfer Learning for Natural Language Processing is now online. It includes a general review of #transferlearning in #NLP as well as new material that I hope will be useful to some. http://ruder.io/thesis/

✴️ @AI_Python_EN

Let's learn more about this amazing #YOLO framework - a supremely fast and accurate framework for object detection. Let's explore YOLO, know why we should use it over other object detection algorithms, the different techniques used by YOLO and then let's implement it in #Python. It’s the ideal guide to gain invaluable knowledge and then apply it in a practical hands-on manner. https://bit.ly/2uq7n9y

✴️ @AI_Python_EN

Learn:

1. linear algebra well (e.g. matrix math)
2. calculus to an ok level (not advanced stuff)
3. prob. theory and stats to a good level
4. theoretical computer science basics
5. to code well in Python and ok in C++

Then read and implement ML papers and *play* with stuff! :-)

Shane Legg

✴️ @AI_Python_EN

CS294-158 Deep Unsupervised Learning Spring 2019

About: This course covers two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-supervised Learning.

Video lectures: https://lnkd.in/eq6ZKAn

#artificialintelligence #deeplearning #generativemodels

✴️ @AI_Python_EN

"AI Needs Better Data, Not Just More Data"

> https://lnkd.in/gR5E7Re

#AI #ArtificialIntelligence #MI #MachineIntelligence
#ML #MachineLearning #DataScience #Analytics
#Data #BigData #IoT #4IR #DataPedigree
#Veracity #Trust #DataQuality #BetterData

✴️ @AI_Python_EN

Data Visualization is a very important step in #DataScience, so we should try to MASTER it.

Here are the useful links for #DataVisualization -

1)Quick and Easy Data Visualizations in Python with Code.
(https://lnkd.in/fXJ-_Y8)

2)10 Useful #Python Data Visualization Libraries for Any Discipline.
(https://lnkd.in/fBxbHwr)

3)Top 50 matplotlib Visualizations – The Master Plots (with full python code).
(https://lnkd.in/fGrnGax)

4)Data Visualization Effectiveness Profile.
(https://lnkd.in/f3v52Fd)

5)The Visual Perception of Variation in Data Displays.
(https://lnkd.in/fm-TbPM)

6)Matplotlib Tutorial – A Complete Guide to Python Plot w/ Examples.
(https://lnkd.in/fFkUgQP)

7)Interactive Data Visualization in Python With Bokeh.
(https://lnkd.in/fEfQAvg)

✴️ @AI_Python_EN

Curated list of awesome ****DEEP LEARNING**** tutorials, projects and communities.



Github Link - https://lnkd.in/fJdpFMn

#deeplearning #machinelearning #datascience #منابع

✴️ @AI_Python_EN

Here are 25 awesome #deeplearning datasets handpicked by our team! We have divided them into 3 categories: Image Processing, Natural Language Processing (#NLP) and Audio/Speech Processing.

https://bit.ly/2DrzUAM

✴️ @AI_Python_EN

Deep Classifiers Ignore Almost Everything They See (and how we may be able to fix it)

Blog by Jorn Jacobsen: https://lnkd.in/eNZt5mn

#MachineLearning #ArtificialIntelligence #ComputerVision #DeepLearning

✴️ @AI_Python_EN