Natural Language Processing, aka Computational Linguistics, is a vast and fascinating subject whose relevance cannot be exaggerated.

It has been greatly hyped but has a number of important applications. It is increasingly part of our daily lives and, for some of us, our jobs.

but here are some books I've found helpful:

- Foundations of Computational Linguistics (Hausser)
- The Handbook of Computational Linguistics (Clark et al.)
- Social Media Intelligence (Moe and Schweidel)
- Natural Language Processing for Social Media (Farzindar and Inkpen)
- Machine Translation (Poibeau)
- Sentiment Analysis: Mining Opinions, Sentiments, and Emotions (Liu)
- Neural Network Methods in Natural Language Processing (Goldberg)

❗️ Natural Language Processing for Social Media
and
❗️ Text Analytics: A Primer

may be of interest. They are brief interviews with two academic authorities on NLP, Anna Farzindar and Bing Liu, respectively.

✴️ @AI_Python_EN

Videos of all sessions at ICLR 2019 (including live stream)

https://www.facebook.com/pg/iclr.cc/videos/?ref=page_internal

✴️ @AI_Python_EN

Top #DataScience and #MachineLearning
#Methods Used in 2018, 2019


https://www.kdnuggets.com/2019/04/top-data-science-machine-learning-methods-2018-2019.html

#AI #ArtificialIntelligence #DeepLearning

✴️ @AI_Python_EN

How to Develop a Convolutional Neural Network From Scratch for MNIST Handwritten Digit Classification
#cnn
https://machinelearningmastery.com/blog/

✴️ @AI_Python_EN

5 Free Object-Oriented Programming Online Courses for Programmers

🌎 Object-Oriented Programming

#Programming

✴️ @AI_Python_EN

FuturePose - Mixed Reality Martial Arts Training Using Real-Time 3D Human Pose Forecasting With a RGB Camera

🌎 Paper
🌎 video

#GAN

✴️ @AI_Python_EN

How I developed a C.N.N. that recognizes emotions and broke into the Kaggle top 10

#GAN #facesrecognize

🌎 link

✴️ @AI_Python_EN

💠 Selection of resources to learn Artificial Intelligence / Machine Learning / Statistical Inference / Deep Learning / Reinforcement Learning

🌍 https://github.com/memo/ai-resources
🌍 https://medium.com/artists-and-machine-intelligence/selection-of-resources-to-learn-artificial-intelligence-machine-learning-statistical-inference-23bc56ba655

✴️ @AI_Python_EN

For better #deepneuralnetwork vision, just add feedback (loops)

🌎 deep neural network


✴️ @AI_Python_EN

How to write better code on data science?


As data scientist you should write code better, here’s the steps

Before start to code, is good to know some implementation machine learning in business


✅ Step 1. Understand Data Science Implementation
https://lnkd.in/fMHtxYP
✅ Step 2. Understand what business want
https://lnkd.in/f396Dqg
✅ Step 3. Know Machine Learning Key Terminology
https://lnkd.in/fCihY9W
✅ Step 4. Know Business Implementation of Data Science
https://lnkd.in/f5aUbBM

After you have clear what to code, here’s the step

1. Following standard style
-> https://lnkd.in/gKZUjVa

2. Use a linter to enforce style standards
-> https://lnkd.in/d_prybR

3. Write modular, generic, object-oriented code -
-> https://lnkd.in/gsynW6Q
-> https://lnkd.in/dx53u53

4. Write unit tests to test your functions and methods
-> https://lnkd.in/dsy-bPu

5. Organizing your code base
-> https://lnkd.in/dviGffH

6. Separate exploration and production development, and develop production code using test-driven development (TDD)
-> https://lnkd.in/dMn-s32

#machinelearning #datascience #supervisedlearning #business

✴️ @AI_Python_EN

Machine Learning Methods - Algorithms and their outputs

#machinelearning #artificialintelligence #datascience #ml #ai #deeplearning

✴️ @AI_Python_EN

There are many misconceptions regarding Null Hypothesis Significance Testing and many disagreements among statisticians about it. Statistics in general is poorly understood in marketing research and the businesses community in my experience.

https://greenbookblog.org/2019/05/08/thats-a-fact-jack/

✴️ @AI_Python_EN

TensorNetwork: A Library for #Physics and
#MachineLearning

“TensorNetwork is an open source library for implementing tensor network algorithms. Tensor networks are sparse data structures originally designed for simulating quantum many-body physics, but are currently also applied in a number of other research areas, including machine learning. Authors demonstrate the use of the API with applications both physics and machine learning, with details appearing in companion papers.”

Paper: https://lnkd.in/e4tPaQG

✴️ @AI_Python_EN

Fundamentals of Clinical Data Science (Open-Access Book) - for healthcare & IT professionals: https://lnkd.in/eacNnjz
#
For more interesting & helpful content on healthcare & data science, follow me and Brainformatika on LinkedIn.

Table of Contents

Part I. Data Collection

- Data Sources
- Data at Scale
- Standards in Healthcare Data
- Research Data Stewardship for Healthcare Professionals
- The EU’s General Data Protection Regulation (GDPR) in a Research Context

Part II. From Data to Model

- Preparing Data for Predictive Modelling
- Extracting Features from Time Series
- Prediction Modeling Methodology
- Diving Deeper into Models
- Reporting Standards & Critical Appraisal of Prediction Models

Part III. From Model to Application

- Clinical Decision Support Systems
- Mobile Apps
- Optimizing Care Processes with Operational Excellence & Process Mining
- Value-Based Health Care Supported by Data Science

#healthcare #datascience #digitalhealth #analytics #machinelearning #bigdata #populationhealth #ai #medicine #informatics #artificialintelligence #research #precisionmedicine #publichealth #science #health #innovation #technology #informationtechnology

✴️ @AI_Python_EN

In the future, you may be fired by an algorithm

#algorithms

✴️ @AI_Python_EN

Deep Learning to Solve Challenging Problems (Google I/O'19)

#DeepLearning

✴️ @AI_Python_EN

Brought to you by: Marketing team of every company.

#fun

✴️ @AI_Python_EN

The worst part when becoming a head of data science/AI/machine learning or whatever at some (larger) companies is that everyone wants something from you:

1. Consultancies want to sell you an AI strategy and then also people to deliver your projects so that you can focus on making nice PowerPoint presentation to higher management 👔
2. Software companies want to sell you ML services or APIs so that you don’t need to build your own models and also worst case knowledge lol 🤖
3. Recruiters want to help you with hiring so that you can focus more on doing point 1 and 2 :) As if 😂

#thatswhymostAITransformationsfail

✴️ @AI_Python_EN

Using Transfer Learning for NLP with Small Data

#TransferLearning #NLP


✴️ @AI_Python_EN

Inviting all passionate data science and deep learning enthusiasts to participate in the Game Of Deep Learning: Deep Learning Hackathon! Deep learning is showing amazing promise for data science and AI, primarily because it’s methods get results and it keeps on improving with more data. Our current state of deep learning ability allows us to perform classification or identification tasks, speech recognition and more at super-human speed.

This hackathon is all about claiming that throne of #deeplearning and seizing career opportunities at Analytics Vidhya . Are you ready to to fight this battle of Deep Learning Throne? Go ahead and register today:
https://lnkd.in/fEXPd-B

✴️ @AI_Python_EN

Building a portfolio for data science does take a considerable amount of time and effort.

It is not a one-time thing. The process of building and improving the portfolio is quite different for people who are working the domain and people who are planning to enter the field.

For people who are working in the domain, getting exposed to different components of data science and different type of projects can improve the existing skillset. Working on personal projects will undoubtedly help showcase your interest even outside work but the value brought by solving a real-world problem for a business stakeholder out-weighs everything else. Working on better projects and getting exposed different forte of projects can certainly help to learn new things.

For people who are trying to enter the domain, it is an iterative process. You build a model, share with the community, get inputs from SMEs and try creating a better one. (Model is an example here). The cycle for aspirants goes like this,
Gain Knowledge -> Build Projects -> Give Interviews -> Work on your mistakes (Gain Knowledge)

I have seen people breaking into the field after one year of continuous learning and iterative effort.

I hope this helps!

#machinelearning #datascience

✴️ @AI_Python_EN