OpenAI’s bot is the first ever to defeat world’s best players in DotA 2 at The International 2017. It is a major step for AI in eSports. The bot was trained through self-play, but some tactics were hardcoded.
The bot doesn’t play DotA in regular 5v5 setup. It can only beat humans in 1v1 play. Team work will be harder to learn. Also, the bot plays only one character and has a few unfair advantages comparing to human players, e.g. it’s likely to have access to exact information such as distance to other players on the map and health.
The field of deep learning is very active, arguably there are one or two breakthroughs every week. Research papers, industry news, startups, and investments. How to keep up with the news?
There are a few newsletters with well-curated links and summaries:
Papers and code:
- AI section of Arxiv.org is useful if you are looking for the latest research papers.
- Gitxiv is a collection of source code links for deep Arxiv papers.
Good regular podcasts about deep learning:
Data is the most important component for building a machine learning model. Recently researchers from Google trained a CNN model for image classification on 300 million images and they demonstrated that even on a scale of hundreds of millions of examples adding more data helps to improve the model performance. Apparently, more data is better. But where can you get large datasets if you are doing research on text classification?
I found nice references to a few large text classification datasets in “Text Understanding from Scratch” paper by Xiang Zhang and Yann LeCun. The paper describes a character-level CNN model for text classification. Authors provide benchmarks of different CNN architectures and a few simple models on a few datasets. More recent version of this paper: “Character-level Convolutional Networks for Text Classification” contains more experimental results but it misses some details on dataset usage: which fields to use, how to truncate long texts, etc. If you are looking for information about datasets, read the older paper. If you want to learn more about the character level CNN models, read the latest paper.
Somebody uploaded the datasets to Google Drive, so you can download them here.
If you have other large text classification datasets, please share in comments to this post.
I started looking at Kaggle competitions to practice my machine learning skills. One of currently running competitions is framed as an image classification problem. Intel partnered with MobileODT to start a Kaggle competition to develop an algorithm which identifies a woman’s cervix type based on images.
The training set contains 1481 images split into three types. Kagglers can use 6734 additional images. Some of them come from duplicate patients. Some of the additional images are lower quality. Test sets for two stages of the competition are available, kagglers have to submit a set of predicted probabilities, one for each of 3 classes, for each image of the test set. The total prize pool is $100,000.
I tried to approach the problem in a naïve way: just get a pre-trained Inception V3 image classification model and fine-tune it on this dataset.
Building a spell checker using deep learning is a great idea. After reading Tal Weiss’s article about the character-based model for spell checking I wanted to run his code, see how well it works for real applications, and work on improvements. This became my fun one-month side project for January 2017.
How will users discover bots when there are thousands of them? App stores just don’t scale. Google can be the first to find a new model of bot discovery. Brad Abrams, group product management of Google Assistant, touched the topic of bot discovery in an episode of O’Reilly Bots Podcast.
NIPS (the Conference and Workshop on Neural Information Processing Systems) is a machine learning and computational neuroscience conference held every December. It was first proposed in 1986, and for a long time, it was a small conference. Interest to NIPS significantly increased when deep learning started demonstrating great results in image recognition, speech recognition, and multiple other areas. Last year NIPS had 2500+ papers submitted and 5000+ people in attendance.
The boom of Machine Learning and AI continues, and for my personal research projects, 2016 year was quite productive. But 2017 has already started. Where to think to in Q1? Continue reading
I treat this blog as my lab journal. I will keep posting random thoughts along with better-written articles on particular topics. This post is an attempt to summarize my activity in some areas in 2016 (see overview of ML and AI in 2016 general in my previous post). Continue reading
2016 was an interesting year. AI winter is over, but this time AI is almost a synonym for deep learning. Major technology companies (Google, Microsoft, Facebook, Amazon and Apple) announced new products and services built using machine learning. DeepMind AlphaGo beat the world champion in Go. Salesforce bought MetaMind to build a deep learning lab. Apple promised to open up its deep learning research.