Top 5 Quora AI and Machine Learning Writers and Their Best Advice

AI and machine learning are effectively changing all the sectors from healthcare and automotive to transportation and education. Quora is the platform where you can ask or answer various questions related to any topic. In the present time, where artificial intelligence is everywhere, questions related to the also arise. Anyone can answer your question but if you want to know who are the best writers? You are in right place.

Here are the top five Quora AI and machine learning writers and their best advice:

Roman Trusov, Facebook AI Research Intern 2016

On the question related to spending money to buy a good GPU for studying deep learning, Roman Trusov advised that if you are serious about studying deep learning, then yes. Understanding an architecture or an algorithm and getting it to work are two very different stories, the only real way to acquire knowledge is to try things for yourself and analyze the results.

If you consider buying multiple cheap GPUs to learn how to work with them – don't. If your framework supports distributed computation, it painlessly does everything. If it doesn't, this is not a task for a beginner, and generally a pain in the rearward.

Zeeshan Zia, Ph.D. in Computer Vision and Machine Learning

On how to prepare for a computer vision research scientist interview? Zeeshan Zia gave really helpful advice saying the two things the interviewer wants to know are whether: (I) you can work as an independent researcher, and (II) whether your expected proportion of research work to software development work matches the position. So prepare accordingly.

Ian Goodfellow, AI Research Scientist

On the question related to problems or motivations of generating images using GAN, Ian Goodfellow said, you can use GANs to:

Generate simulated training data and simulated training environments, fill in missing data, train a classifier with semi-supervised learning, do supervised learning where the supervision signal says that any one of multiple correct answers are acceptable, instead of just having one specific answer you request for each training example, and more.

Clayton Bingham, Neural Engineering Researcher

When the question was asked on what's trending in machine learning (outside of deep learning)? Clayton Bingham's answer was perfect in all manners.

Bingham said he doesn't know about trending, but he surely knows about a powerful method, outside of mainstream ML, Volterra Kernels which is demonstrated to have tremendous flexibility, interpretability, and the advantage of the relative ease of implementation in VLSI/FPGA hardware.

Xavier Amatriain, leading Engineering at Quora

When asked, what are some best practices for training machine learning models? Xavier's answer was only one word "Metrics". You should pick an offline optimization metric that correlates as well as possible to the product objectives. Many times, a good proxy for the product objectives can be an online A/B test result or some other online metric.