Sign in

An AI architect who is on a mission to inspire the next generation of innovators. Author of “Artificial Intelligence: Unorthodox Lessons” at


Three essential pillars to creating a solid data strategy

Photo by Zane Lee on Unsplash

Here, I want to define data strategy in simple words, and help you create one for your organization. In recent years, data has become a strategic resource for companies, and every company must create a data strategy to not lose the game to its competitors. The main question is how? To answer, you have to, first, understand what data strategy is. Then, you must create a plan tailored to your organization knowing the limitations and capabilities. In short, a data strategy has three essential pillars: (1) Value, (2) Collection, and (3) Architecture. Data strategy does have other aspects which I…

An answer to a philosophical dilemma in data science

Photo by Giammarco Boscaro on Unsplash

This is a philosophical dilemma in data science. What feature-selection approach should we use: cherry-picked or exhaustive? The answer is “it depends”. Here, the “cherry-picked” means selecting a small set of meaningful features that can be explained very well; the “exhaustive” means selecting all possible combinations of the features in the dataset. I come from the tribe of ML experts who believe over-complexity doesn’t help, at least in most cases. Saying that you may conclude I am a fan of the cherry-picked approach. That is not completely true though. In this article, I want to compare these two feature selection…

The intersection of Databricks, Python, and Docker

Photo by Clay Banks on Unsplash

When you start working with Databricks, you will reach the point that you decide to code outside of the Databricks and remotely connect to its computation power, a.k.a. Databricks Cluster. Why? Mostly because one of the main features of Databricks is its Spark job management that can make your life easy. Using this service, you can submit a series of Spark jobs to a large-scale dataset and get back your results in a matter of seconds; thanks to its Spark engines. …

Artificial Intelligence, Future

A deeper look into the Big Ideas 2021 created by the ARK Invest

Photo by British Library on Unsplash

I was talking with a friend of mine who is experienced in the stock market. He was analyzing the Big Ideas 2021 deck created by the ARK Invest’s team where they presented their thoughts on emerging technologies and their future opportunities. My friend asked me to review the Deep Learning section and share my opinion with him. After reviewing the deck, I first admired the quality of the content. However, I found parts that I was not aligned with and parts that I found insightful. …

Fairness and Bias

AI ethical challenges: prejudices and biases, economic inequality, and global warming

Photo by Gyan Shahane on Unsplash

Before you start reading this article, I want you to drop down your guard. We are all aware of the power of artificial intelligence. I have studied and worked in this field for the past 15 years. So, I obviously do not want to devalue AI in this letter; however, I want to simply advocate for building AI solutions more responsibly.

If you care about economic inequality, you should use huge ML models such as GPT-3 with 175 billion parameters with caution. When a model has that many parameters, you need high computation power to benefit from it. These models…

Life Lessons

The way I cope with the uncertainties and madness in 2020

Photo by Fernando @cferdo on Unsplash

We are in the final days of 2020, a year full of uncertainty and madness. The pandemic created lots of confusion for me, as well as for everyone else. I was in the early days of building my own business when the pandemic hit the world. I had left my previous job for something more exciting at the end of 2019. It was time for me to focus on building a new business if the pandemic would have let me.

I am an engineer by education but an entrepreneur by heart. I took a doctorate from the University of British…

AI Consulting Series

Whether you need or offer an AI consulting service, you will benefit from this playbook

Photo by Robert Tudor on Unsplash

In recent years, I offered artificial intelligence or AI consulting services to several companies. Most of them suffered from a lack of AI knowledge. The lack of knowledge may create opportunities for experts to provide AI consulting services; however, it creates many challenges to defining project requirements and deliverables. I went through most of these challenges, and I want to share my experience dealing with them. If you want to offer or need an AI consulting service, I highly recommend reading this article.

Business Understanding — Step 0

In this step, you must determine the objectives and requirements of the project. You must identify what…


Gensim or spaCy? It doesn’t matter if you don’t know the fundamentals of Word2Vec models.

Photo by Matt Briney on Unsplash

We encode text data such as words or sentences into high-dimensional vectors for various machine learning tasks. In the past, we mostly used encoders such as one-hot, term-frequency, or TF-IDF. However, the semantic and syntactic information of words were not captured in these techniques. The Word2Vec models allow us to encode words in more meaningful ways and much more! In this article, I want to describe the Word2Vec model and its beautiful applications. Plus, I explain why Word2Vec models are simple yet revolutionary.

I decided to write this article, after receiving many positive feedbacks on my previous article titled How…

NLP-in-Production Series

Along with some insights to prevent common mistakes in computing sentence embedding

Photo by Katya Austin on Unsplash

We often need to encode text data, including words, sentences, or documents into high-dimensional vectors. The sentence embedding is an important step of various NLP tasks such as sentiment analysis and extractive summarization. A flexible sentence embedding library is needed to prototype fast and to tune for various contexts.

In the past, we mostly used encoders such as one-hot, term-frequency, or TF-IDF (a.k.a., normalized term-frequency). However, the semantic and syntactic information of words were not captured in these techniques. The recent advancements allow us to encode sentences or words in more meaningful forms. The word2vec technique and the BERT language…

Pedram Ataee, PhD

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store