🐼🤹♂️ pandas trick:
Two easy ways to reduce DataFrame memory usage:
1. Only read in columns you need
2. Use 'category' data type with categorical data
Example:
df = pd.read_csv('file.csv', usecols=['A', 'C', 'D'], dtype={'D':'category'})
#Python #DataScience
✴️ @AI_Python_EN
Two easy ways to reduce DataFrame memory usage:
1. Only read in columns you need
2. Use 'category' data type with categorical data
Example:
df = pd.read_csv('file.csv', usecols=['A', 'C', 'D'], dtype={'D':'category'})
#Python #DataScience
✴️ @AI_Python_EN
Statistical methods can and are applied to qualitative data (e.g. text). The raw data first need to be converted to a form, or represented in a way, that can be quantitatively analyzed.
It can be done by man or, increasingly, machine. This would be the case whether cluster analysis, factor analysis, deep learning or some other method is used to analyze the data.
A very simple example is cluster or factor analyzing open end codes from a consumer survey, or using them in key driver regression.
This predates AI by many years, though machine coding would now be the preferred approach in many instances.
Sparse data can be a concern, but with rapid declines in the cost of survey data collection, this is now more feasible since very large samples can be collected at reasonable cost and within a realistic time frame.
To be clear, my original motivation for this post was not to push an alternative to standard close-ended questioning, but a response to confusion about AI I frequently encounter. However, with data of sufficient quality, complex analytics which tie attitudes, behavior and demographics together, perhaps combined simultaneously with segmentation, is possible with this alternative method. AI in some form may play a part but is not absolutely essential. The basic idea goes back nearly a century.
✴️ @AI_Python_EN
It can be done by man or, increasingly, machine. This would be the case whether cluster analysis, factor analysis, deep learning or some other method is used to analyze the data.
A very simple example is cluster or factor analyzing open end codes from a consumer survey, or using them in key driver regression.
This predates AI by many years, though machine coding would now be the preferred approach in many instances.
Sparse data can be a concern, but with rapid declines in the cost of survey data collection, this is now more feasible since very large samples can be collected at reasonable cost and within a realistic time frame.
To be clear, my original motivation for this post was not to push an alternative to standard close-ended questioning, but a response to confusion about AI I frequently encounter. However, with data of sufficient quality, complex analytics which tie attitudes, behavior and demographics together, perhaps combined simultaneously with segmentation, is possible with this alternative method. AI in some form may play a part but is not absolutely essential. The basic idea goes back nearly a century.
✴️ @AI_Python_EN
We Can All Become Video Game Characters With This AI
Video: https://www.youtube.com/watch?v=Y73iUAh56iI
Paper: https://arxiv.org/abs/1904.08379
Video: https://www.youtube.com/watch?v=Y73iUAh56iI
Paper: https://arxiv.org/abs/1904.08379
Adapters: A Compact and Extensible Transfer Learning Method for NLP
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
Medium
Adapters: A Compact and Extensible Transfer Learning Method for NLP
Adapters obtain comparable results to BERT on several NLP tasks while achieving parameter efficiency.
Machine Learning Free Course with TensorFlow APIs by Google
https://developers.google.com/machine-learning/crash-course/
https://developers.google.com/machine-learning/crash-course/
Google for Developers
Machine Learning | Google for Developers
image_2019-06-23_22-33-48.png
149.8 KB
I've been thinking a bit about the growing practice of fine-tuning generic pretrained models: first in computer vision, now NLP (highly recommend Sebastian Ruders great article on this http://ruder.io/nlp-imagenet/ )...Last time I mentioned this, people were skeptical that RL would be next.
✴️ @AI_Python_EN
✴️ @AI_Python_EN
Death by algorithm: the age of killer robots is closer than you think
🔗 https://www.vox.com/2019/6/21/18691459/killer-robots-lethal-autonomous-weapons-ai-war
#machinelearning
✴️ @AI_Python_EN
🔗 https://www.vox.com/2019/6/21/18691459/killer-robots-lethal-autonomous-weapons-ai-war
#machinelearning
✴️ @AI_Python_EN
All materials of berkeley ai Deep Unsupervised Learning now up:
https://sites.google.com/view/berkeley-cs294-158-sp19/home
✴️ @AI_Python_EN
https://sites.google.com/view/berkeley-cs294-158-sp19/home
✴️ @AI_Python_EN
Google
CS294-158-SP19 Deep Unsupervised Learning Spring 2019
About: This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-supervised Learning. Recent advances in generative models have made it possible to realistically model high-dimensional raw data…
Using #AI To Analyze Video As Imagery: The Impact Of Sampling Rate
https://buff.ly/2IBFRO8
#ArtificialIntelligence #MachineLearning #DeepLearning #robotics
✴️ @AI_Python_EN
https://buff.ly/2IBFRO8
#ArtificialIntelligence #MachineLearning #DeepLearning #robotics
✴️ @AI_Python_EN
Bayesian Optimization with Binary Auxiliary Information
https://deepai.org/publication/bayesian-optimization-with-binary-auxiliary-information … by Yehong Zhang et al.
#ReinforcementLearning #Hyperparameter
✴️ @AI_Python_EN
https://deepai.org/publication/bayesian-optimization-with-binary-auxiliary-information … by Yehong Zhang et al.
#ReinforcementLearning #Hyperparameter
✴️ @AI_Python_EN
Best Paper Finalist (top 1% of accepted papers) Check it out!
http://openaccess.thecvf.com/content_CVPR_2019/html/Ribera_Locating_Objects_Without_Bounding_Boxes_CVPR_2019_paper.html
http://openaccess.thecvf.com/content_CVPR_2019/html/Ribera_Locating_Objects_Without_Bounding_Boxes_CVPR_2019_paper.html
Comparison of different #MachineLearning approaches for neuroimaging data
Main take-aways - prediction accuracy increased once N ≥ 400
- Substantial effect of pipeline on accuracies: Is this the new p-hacking?
https://buff.ly/2NdaJcv
✴️ @AI_Python_EN
Main take-aways - prediction accuracy increased once N ≥ 400
- Substantial effect of pipeline on accuracies: Is this the new p-hacking?
https://buff.ly/2NdaJcv
✴️ @AI_Python_EN
Theory of the Frequency Principle for General Deep Neural Networks.
http://arxiv.org/abs/1906.09235
✴️ @AI_Python_EN
http://arxiv.org/abs/1906.09235
✴️ @AI_Python_EN
arXiv.org
Theory of the Frequency Principle for General Deep Neural Networks
Along with fruitful applications of Deep Neural Networks (DNNs) to realistic
problems, recently, some empirical studies of DNNs reported a universal
phenomenon of Frequency Principle...
problems, recently, some empirical studies of DNNs reported a universal
phenomenon of Frequency Principle...
Artificial Intelligence can write creative & convincingly human-like captions for any image. Great work by IBM Research at #cvpr2019 In order to ensure the generated captions did not sound too unnatural, the work employed conditional GAN training Read
https://arxiv.org/pdf/1805.00063.pdf
✴️ @AI_Python_EN
https://arxiv.org/pdf/1805.00063.pdf
✴️ @AI_Python_EN
#Machineearning for Everyone
http://bit.ly/2RvRRnj
#AI #ML #DataScience #Algorithms
✴️ @AI_Python_EN
http://bit.ly/2RvRRnj
#AI #ML #DataScience #Algorithms
✴️ @AI_Python_EN
A Gentle Introduction to Upsampling and Transpose Convolution Layers for GANs
Generative Adversarial Networks, or GANs, are an architecture for training generative models, such as deep convolutional neural networks for generating images
✴️ @AI_Python_EN
Generative Adversarial Networks, or GANs, are an architecture for training generative models, such as deep convolutional neural networks for generating images
✴️ @AI_Python_EN
The #xtensor article series continues! Learn everything about xtensor constructors and initializer lists in
https://medium.com/@johan.mabille/how-we-wrote-xtensor-3-n-the-constructors-65a177260638
✴️ @AI_Python_EN
https://medium.com/@johan.mabille/how-we-wrote-xtensor-3-n-the-constructors-65a177260638
✴️ @AI_Python_EN
This is incredible. This paper from MIT Computer Science & Artificial Intelligence Lab presented at #cvpr2019 shows how to reconstruct a face from speech patterns.
https://speech2face.github.io
✴️ @AI_Python_EN
https://speech2face.github.io
✴️ @AI_Python_EN