By Sanjeev Agrawal— 6min read.
Airlines are arguably more operationally complex, asset-intensive, and regulated than hospitals, yet the best performers are doing a better job by far than most hospitals at keeping costs low and make a decent profit while delivering what their customers expect.
Teaching a Variational Autoencoder (VAE) to draw MNIST characters
By Felix Mohr – 4 min read.
Autoencoders are a type of neural network that can be used to learn efficient codings of input data. Given some inputs, the network first applies a series of transformations that map the input data into a lower dimensional space.
Improving Airbnb Yield Prediction with Text Mining
By Joaee Chew – 11 min read.
Airbnb is a popular home-sharing platform enabling people all over the world to share their unique accommodations. For potential hosts, this could be a profitable option for their empty vacation homes, spare rooms or even extra beds.
Deep Learning Specialization by Andrew Ng – 21 Lessons Learned
By Ryan Shrott – 10 min read.
I recently completed all available material (as of October 25, 2017) for Andrew Ng’s new deep learning course on Coursera. There are currently 3 courses available in the specialization.
Artificial Intelligence Applications: Data Science Meets Procurement
By Shamli Prakash – 4 min read.
One of the most critical functions in organizations, but often less appreciated than it should be, is the Procurement function. Somehow it rarely has the glitz and glamour associated with its more modish counterparts like Marketing, Finance or Technology.
One Bubble Chart, Comparing 10 Data Visualization Tools
By Susan Li – 7 min read.
For anyone who wants to learn data analysis and visualization, there is no shortage of "best tools" articles online telling you what to choose. I won’t attempt to create a list, as there are simply too many tools to enumerate.
Dog Breed Classification using Deep Learning: hands-on approach
By Kirill Panarin – 8 min read.
Several days ago I noticed Dog Breed Identification challenge hosted by Kaggle. The goal is to build a model capable of doing breed classification of a dog by just "looking" into its image.