By Jonny Brooks-Bartlett – 15 min read.
Most articles about how to "complete" a data science task usually discuss how to write an algorithm to solve a problem. For example how to classify a text document or forecast financial data. Learning how to do these things can be vital knowledge for a data scientist if it falls within their remit.
Convolutional Neural Networks: The Biologically-Inspired Model
By James Le – 14 min read
It is incredible how human brains can unfold an image consisting of just arrays of R,G,B values. How about computers? How can we begin to write an algorithm that can reason about the scene like I just did above? How can we get the right data that can support the inferences we make?
Making Music: When Simple Probabilities Outperform Deep Learning
By Haebichan Jung – 9 min read
How I discovered a problem of using deep learning to make music, and solved it by creating my own original model.
How to Run Parallel Data Analysis in Python using Dask Dataframes
By Luciano Strika – 5 min read
If you work on Big Data, you know if you’re using Pandas, you can be waiting for up to a whole minute for a simple average of a Series, and let’s not even get into calling apply. And that’s just for a couple million rows! When you get to the billions, you better start using Spark or something.
Named Entity Recognition and Classification with Scikit-Learn
By Susan Li – 7 min read
Named Entity Recognition and Classification (NERC) is a process of recognizing information units like names, including person, organization and location names, and numeric expressions including time, date, money and percent expressions from unstructured text.
A Day in the Life of a Marketing Analytics Professional
By Chris Dowsett – 7 min read
Marketing Analytics is a multifaceted but often misunderstood practice. Here’s an example day to highlight the diversity of the role.
Changing The Engineer’s Mindset : From How to Why
By Jessie Smith – 7 min read
In a world inundated with data and overridden with information, where we discover what the weather outside is from an invisible cloud in the comfort of our homes; it is due time to take a step back and ask some important questions.
Tutorial: Double Deep Q-Learning with Dueling Network Architecture
By Fabio M. Graetz – 9 min read
If you are as fascinated by Deep Q-Learning as I am but never had the time to understand or implement it, this is for you: In one Jupyter notebook I will 1) briefly explain how Reinforcement Learning differs from Supervised Learning, 2) discuss the theory behind Deep Q-Networks (DQN) by telling you where you find the respective explanations in the papers and what they mean and 3) how to implement the components needed to make it work in python and tensorflow.
Automatic Speech Recognition Data Collection with Youtube V3 API, Mask-RCNN and Google Vision API
By 黃功詳 Steeve Huang – 8 min read
With the rapid development of Machine Learning, especially Deep Learning, Speech Recognition has been improved significantly. Such technology relies on large amount of high-quality data. However, the models built for non-popular languages performs worse than those for the popular ones such as English.
How to build a non-geographical map #1
By Fanny Kassapian – 8 min read
To visualize your non-geographical data in a map-like way, you need to think of each element (or point on the map), as defined by a certain set of features (or attributes).
