Vadim Smolyakov

Machine Learning Engineer

Microsoft

I am a Machine Learning Engineer at Microsoft. I was a PhD student in the Sensing, Learning, and Inference (SLI) lab at MIT CSAIL.

My research interests are in probabilistic modeling and deep learning in application to natural language processing and computer vision.

I completed my MASc degree specializing in wireless communications and BASc degree in Engineering Science at the University of Toronto

In the past, I worked as a Data Scientist at Microsoft, Rue Gilt Groupe and Shopify. I was also at Qualcomm and Max Linear as a systems researcher and a digital baseband designer.

I'm passionate about growth, self-development, education, and sharing what I learn with others.

News

Books

ML Algorithms in Depth

Algorithmic ML

Machine Learning Algorithms in Depth dives into the design and underlying principles of some of the most exciting machine learning (ML) algorithms in the world today. With a particular emphasis on probabilistic algorithms and computer science concepts. In this book, you'll explore the underlying mathematics and derive the algorithms yourself from first principles.

Life Guide Now

Life Guide Now: on life, goals, philosophy, success.

Today is an important day, it is a day to breathe, to live, to learn, to create, to leave a legacy. Tomorrow is a bright unknown, open to possibilities. Life guide now is a book to help you discover your purpose, set goals, build success habits, and reflect on your journey. Every second of every day counts and today is no exception.

Projects

Life Guide Now

Life Guide Now

Your personal life coach

Life Guide Now started as my passion project in order to share my life experiences and lessons learned with others. It is more important now than ever to know yourself: know your purpose, what makes you happy and fulfilled in life; and build strong foundations of goal setting, success habits and self-reflection. In my instagram channel, I share practical advice on how to achieve these goals!

YouTube

ML explained

Deep dives on ML algorithms

My YouTube channel "ML explained" is dedicated to deep dives on machine learning algorithms. I explain how different algorithms work from first principles, their pros and cons, and practical applications. Check it out if you want to learn more about algorithmic machine learning!

Open Source

GitHub Repos

Machine Learning and Deep Learning projects

Check out my GitHub repositories for various machine learning and deep learning projects. I share code implementations, experiments, and tutorials on different ML topics.

Research and Development

Responsible AI

Users in charge of information

V. Smolyakov, S. Ranganathan, S. Narayanan, J. Shotts, M. Todorova, E. Nouri, et al. "Responsible AI: Users in Charge of Information", 2020 [video]

Hyper-Personalization

Intent classification model for intelligent edge

V. Smolyakov, H. Liu, L. Shan, J. Liang, B. Nitta, "Intent Classification for Intelligent Edge", 2019 [slides]

Bayesian Nonparametric Models

Modeling driver behavior using HDP Split-Merge sampling algorithm

V. Smolyakov, J. Straub, S. Zheng, and J. W. Fisher III, "Bayesian Nonparametric Modeling of Driver Behavior using HDP Split-Merge Sampling Algorithm", 2018 [arXiv]

Minibatch Gibbs Sampling

Optimizing mini-batch size for Gibbs sampling algorithms on big data

V. Smolyakov, Q. Liu, J. W. Fisher III, "Adaptive Scan Gibbs Sampler for Large Scale Inference Problems", 2018 [arXiv] [slides]

Beamforming

mm-wave beam-search for MIMO wireless communication

V. Smolyakov, J. Ryu, S. Subramanian, "mm-wave beam search", 2013 [slides]

K-Best MIMO Detector

High-Throughput Digital Architecture for K-Best Multi-Input Multi-Output Detector

D. Patel, V. Smolyakov, M. Shabany, and P. G. Gulak, "VLSI Implementation of a WiMAX/LTE Compliant Low-Complexity High-Throughput Soft-Output K-Best MIMO Detector", 2010 [PDF]