AVBytes: AI & ML Developments this week – Stanford’s NLP Course Projects, R Package for Anomaly Detection, Create Deep Learning Dataset, etc.
Developments in AI & ML are happening at break neck speed. Hardly a day goes without hearing about a new development in these field. It is difficult to stay on top of these developments.
This was one of the main reasons behind launching AVBytes and the response from community has been phenomenal.
The past week saw some intriguing developments in machine learning and deep learning. Stanford released a list of all its NLP course projects for 2018 (it’s a goldmine of knowledge), the Google Research team unveiled its deep neural network to extract audio by looking at a person’s face, a R package was released to deal with anomalies in time series, and many other developments happened this week which we have covered under the AVBytes umbrella.
Scroll down to view all the articles from last week. Also, Subscribe here to get AVBytes delivered directly to your inbox daily!
Below is a round-up of all the happenings in the last week. Click on each title to read the full article.
- Stanford’s NLP Course Projects are Available Online and they’re Super Impressive: Interested in NLP? Here’s a knowledge goldmine! Stanford has released the latest course projects on NLP and they are super impressive! Which one caught your eye? Let us know in the comments section.
- This AI can Create your 3D Avatar using just your Smartphone Camera!: Want to see how you look in your digital 3D form? Thanks to AI, you can do this now with incredible accuracy! Check out the algorithm behind this latest research.
- Add Objects to Paintings and Images Seamlessly with this Amazing Python Script: This algorithm will blow your mind! It allows you to add external objects to paintings and you won’t be able to tell the difference in the final image. Check out the amazing examples of the algorithm in action inside.
- Google’s Neural Network Extracts the Audio Source by Looking at a Person’s Face: Ever been to a noisy party and struggle to hear anything? The Google Research team has come up with a convolutional neural network model that looks at a person’s face and separates audio speech for each individual in the video!
- XceptionNet is a Deep Learning Algorithm that Detects Face Swaps in Videos: Forged face swap videos are becoming a menace! XceptionNet is a deep learning algorithm that detects these fake videos with impressive accuracy.
- ‘Anomalize’ is a R Package that Makes Anomaly Detection in Time Series Extremely Simple and Scalable: Anomaly detection is a tricky task in a time series dataset. Here’s a R package called Anomalize that makes it ever so simple and scalable! Tell us your experience using it!
- Develop Your Own Personal Deep Learning Image Dataset using this Python Script: This python script enables you to download hundreds of Google images. Create your own personal deep learning image dataset to practice your DL skills!
The above AVBytes were published from 9th to 15th April, 2018.
Since I am a R user, the ‘anomalize’ package is a must-have for dealing with time series data. It makes life so much more easier! Stanford’s NLP course projects were also an eye opener – the quality of research papers released by the students is mind-boggling. What excited you the most about this week?
Subscribe here to get daily AVBytes in your inbox!