An advantage probabilistic models such as logistic regression have over hard classifiers is that we are not bound to positive/negative dichotomies.

A customer with purchase probability of .51 may be very different from one with a probability of .99.

Moreover, our model may perform very well in some prediction ranges and fall down badly in others. Having this information can help us diagnose the causes, improve our model and learn about our customers.

What about non-linearities and moderated effects (interactions)? With a little extra work, these can be identified and incorporated into the model.

What about customer heterogeneity (for example)? Any model can be boosted and bagged and mixture modeling is also (for me) an attractive option.

Methods such as logistic regression also have advantages over some other methods when there are more than two classes (groups) and when the sizes of the classes are very different (class imbalance).

✴️ @AI_Python_EN

SinGAN: Learning a Generative Model from a Single Natural Image

Shaham et al.: https://lnkd.in/eUWJ6Ta

#ArtificialIntelligence #DeepLearning
#GenerativeAdversarialNetworks
✴️ @AI_Python_EN

The Best and Most Current of Modern Natural Language Processing

Blog by Victor Sanh: https://lnkd.in/emch8gG

#NaturalLanguageProcessing #MachineLearning #NLP #DeepLearning #Research

✴️ @AI_Python_EN

omplete Deep Learning Drizzle

Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!

GitHub by Marimuthu K.: https://lnkd.in/eTUp4Hi

B. For Business Applications you can see at
Data Science Process https://lnkd.in/fMHtxYP
Data Visualization in Business https://lnkd.in/fYUCzgC
Understand How to answer Why https://lnkd.in/f396Dqg
Know Machine Learning Key Terminology https://lnkd.in/fCihY9W
Understand Machine Learning Implementation https://lnkd.in/f5aUbBM
Machine Learning Applications on Marketing https://lnkd.in/fUDGAQW
Machine Learning Applications on Retail https://lnkd.in/fihPTJf

#machinelearning #analytics #datascience #artificialintelligence

#artificialintelligence #deeplearning #machinelearning #reinforcementlearning

✴️ @AI_Python_EN

"Neural network models are inspired by the biological brain—the analogy is that just as the neurons in brains calculate something and are connected, neurons in artificial neural networks also calculate and are connected, forming networks of interconnected neurons, also called units. In reality, the analogy ends there; biological brains are complicated structures, and there is still a lot that we don't know about how they work. So, if someone asks you whether your neural network model works like a brain, the answer is an emphatic, No." Alvaro Fuentes in "Hands-On Predictive Analytics with Python: Master the complete predictive analytics process, from problem definition to model deployment." Packt Publishing.

✴️ @AI_Python_EN

Extracting Features from Text - A Step-by-Step NLP Guide to Learn ELMo Python - Prateek Joshi.


#machinelearning #artificialintelligence #datascience #ml #ai #deeplearning #python #nlp #tutorial

✴️ @AI_Python_EN

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Researchers from #GoogleAi and #Stanford published work today in #Nature that shows great potential to use machine learning to help catch more lung cancer cases earlier and increase survival likelihood.

Link: https://lnkd.in/fUMtA-3

#LungCancer #Cancer #biolearning #healthcare #DL

✴️ @AI_Python_EN

#ArtificialNeuralNetworks (ANN) were supposed to replicate the architecture of the human brain, yet till about a decade ago, the only common feature between #ANN and our brain was the nomenclature of their entities (for instance – neuron). ANN architectures have become extremely useful across industries.

https://bit.ly/2Et1wpl

✴️ @AI_Python_EN

Download pdf, or get your copy, of AutoML: Methods, Systems, Challenges.

https://lnkd.in/gnWgVt8
#datascience
#machinelearning


✴️ @AI_Python_EN

Which doodles are human-drawn and which are AI-generated? Berkeley researchers Forrest Huang et al created a #neuralnetwork that can generate sketches based on text descriptions:
http://bit.ly/2LZSHJN


✴️ @AI_Python_EN

The basics of NLP and real time sentiment analysis with open source tools

#NLP #sentimentanalysis #opensource

The basics of NLP and real time sentiment analysis with open source tools
✴️ @AI_Python_EN

Quant types often dismiss qualitative research as subjective and, therefore, unscientific.

Though a quant type myself, I must dissent. Not on the grounds that qualitative research is purely objective, but on the grounds that most quantitative research in any field requires a substantial amount of subjective judgment on the part of the research team, statisticians included.

Were this not the case, there would be little need to reproduce and replicate quantitative research findings, apart from concerns about fraud.

There would be far fewer journal articles, books and conferences, and little need for #meta_analysis. All #AI would give us the same answers, too.

✴️ @AI_Python_EN

letting beginners and experts alike learn about SAP HANA.
Download here --> https://lnkd.in/eTtdvi4

End to end Machine learning platform.
Bring your own language and microservices.Java, Node.js and Python are the officially supported languages.

SAP HANA is an ACID-compliant database and application development platform. You can use advanced data processing capabilities—text, graph, spatial, predictive, and more—to pull insights from all types of data.

#machinelearning #artificialintelligence #datascience #ml #ai #deeplearning #python #R #java #SQL

✴️ @AI_Python_EN

Data-Efficient Image Recognition with Contrastive Predictive Coding

Hénaff et al.: https://lnkd.in/eMDhrU8

#ArtificialIntelligence #ComputerVision #MachineLearning

✴️ @AI_Python_EN

Full Stack Deep Learning Bootcamp
(Most of) Lectures of Day 1:
https://fullstackdeeplearning.com/march2019

#ArtificialIntelligence #DeepLearning #MachineLearning

✴️ @AI_Python_EN

Probabilistic Graphical Models

Spring 2019 • Carnegie Mellon University

Lisa Lee
https://sailinglab.github.io/pgm-spring-2019/lectures/

✴️ @AI_Python_EN

Deep Learning lecture
The full deck of (600+) slides, by Gilles Louppe:
https://glouppe.github.io/info8010-deep-learning/pdf/lec-all.pdf

#ArtificialIntelligence #DeepLearning #MachineLearning

✴️ @AI_Python_EN

SOD is an embedded, modern cross-platform computer vision and machine learning software library that expose a set of APIs for deep-learning, advanced media analysis & processing including real-time, multi-class object detection and model training on embedded systems with limited computational resource and IoT devices.

SOD - An Embedded #ComputerVision & #MachineLearning Library
https://sod.pixlab.io/
api https://sod.pixlab.io/api.html
samples https://sod.pixlab.io/samples.html
guide https://sod.pixlab.io/intro.html
github https://github.com/symisc/sod

✴️ @AI_Python_EN

Moving Camera, Moving People: A #DeepLearning Approach to Depth Prediction

http://ai.googleblog.com/2019/05/moving-camera-moving-people-deep.html

✴️ @AI_Python_EN

"Storytelling with Data: A Data Visualization Guide for Business Professionals" by Cole Nussbaumer Knaflic

I've just come across this first (2015) edition, and there now may be a second edition out. Here's the link to the PDF:

https://lnkd.in/fJSN7ci

✴️ @AI_Python_EN

Estimators, Loss Functions, Optimizers —Core of ML Algorithms

https://towardsdatascience.com/estimators-loss-functions-optimizers-core-of-ml-algorithms-d603f6b0161a]

✴️ @AI_Python_EN