Introduction to Bayesian Networks

Bayesian networks are a type of probabilistic graphical model that uses Bayesian inference for probability computations. Bayesian networks aim to model conditional dependence, and therefore causation, by representing conditional dependence by edges in a directed graph. Through these relationships, one can efficiently conduct inference on the random variables in the graph through the use of factors.

Failing Fast with DeepAR Neural Networks for Time-Series

In the world of machine learning, failing fast is crucial. When considering AWS’s DeepAR, a recurrent neural-network (RNN) time series algorithm, there are several questions to ask when sizing up the ability to fail fast:
1. Is DeepAR appropriate for the problem at hand / are there enough individual time series (at least in the hundreds)?
2. Can a pipeline be built quickly?
3. Can you harness hyperparameter settings to create a quality model?
4. Can the model performance be analyzed efficiently?
5. Have you read forums to understand nuances of the algorithm?

The Emergence of Cooperative and Competitive AI Agents

Collaboration and competition are two of the key pillars on the evolution of human societies and essential to our evolution as species. Billions of people inhabit our planet grouped in millions of communities, each with their own beliefs about politics, economics, religion, social justice or sports. While those beliefs make each of us unique, they haven’t prevented us from coming together to achieve amazing things. Those group efforts are typically guided by the cooperative and competitive dynamics between its members which constitutes the foundation of collective intelligence. From that perspective, every area of human knowledge can be traced back to a collaborative and/or competitive dynamic in a specific community. In artificial intelligence(AI), most of the recent breakthroughs have been constrained to individual agents operating in highly constrained environments. Enabling collective knowledge building dynamics is essential to the evolution of AI and it requires fomenting organic competitve and collaboration between AI agents. Recently, Science published a paper from Google’s subsidiary DeepMind highlighting their fascinating experiences building collaboration and competition in AI agents playing the Quake III Capture the Flag(CTF) game.