10 Deadly Sins of Machine Learning Model Training

Location cups

10 Deadly Sins of Machine Learning Model Training. ML model training is the most time-consuming and resource-expensive part of the overall model-building journey. Training by definition is iterative, but somewhere during the iterations, mistakes seep into the mix. In this article, I share the ten deadly sins during ML model training — these are the most common as well as the easiest to overlook.

Read More

Guide to MBIRL – Model Based Inverse Reinforcement Learning

In this article, we are going to discuss one such algorithm-based Inverse Reinforcement Learning. The proposed MBIRL algorithm learns loss functions and rewards via gradient-based bi-level optimization.  This framework builds upon approaches from visual model-predictive control and IRL. This new MBIRL algorithm is a collaborative work of Neha Das (Facebook AI Research)*; Sarah Bechtle (Max Planck Institute for Intelligent Systems); Todor Davchev (University of Edinburgh); Dinesh Jayaraman (University of Pennsylvania); Akshara Rai (Facebook); Franziska Meier (Facebook AI Research) and was accepted at 4th Conference on Robot Learning (CoRL 2020), Cambridge MA, USA in a Conference Paper.

Read More

Six stage gates to a successful AI governance


Responsible use of AI should start with a detailed assessment of the key risks posed by AI [1], followed by a good understanding of the principles that should be followed [2], and then the governance of AI from a top-down and end-to-end perspective [3]. We have discussed these in our previous articles [1, 2, 3]. In this article, we focus on the first line of defense and dive into the nine-step data science process [4] of value scoping, value discovery, value delivery, and value stewardship and highlight the dimensions of governance.

Read More

Is Google’s AI research about to implode?

Platform game

What does Timnit Gebru’s firing and the recent papers coming out of Google tell us about the state of research at the world’s biggest AI research department. The high point for Google’s research in to Artifical Intelligence may well turn out to be the 19th of October 2017. This was the date that David Silver and his co-workers at DeepMind published a report, in the journal Nature, showing how their deep-learning algorithm AlphaGo Zero was a better Go player than not only the best human in the world, but all other Go-playing computers.

Read More

My machine learning model does not learn. What should I do?

If you work with data in general, and machine learning algorithms in particular, you might be familiar with that feeling of frustration when a model really does not want to learn the task at hand. You have tried it all, but the accuracy metric just won’t rise. What next? Where is the problem? Is this an unsolvable task or is there a solution somewhere you’re not aware of?

Read More

Why building a Machine Learning Model is like cooking

The first step in building a machine learning model is to prepare the data. This may involve pulling raw data from a variety of sources to load into a database. Likewise, the first step in cooking is to get the ingredients (the data). You may need to go to the grocery store to buy ingredients you don’t have at home (pull from a variety of sources).

Read More