Source: Lynda.com via Google Images

We at SquadStack are currently focusing heavily on building Auctm (Smart Assistant for real estate brokers and agents in the US). As a Data Scientist, it had been a great opportunity to work with an amazing Product Team and learn about end to end product development involving the deployment of many Data Science driven features and Machine Learning models. Since the product thesis involves Data Science at its core, cross-functional interactions with various functions like Product, Design, Engineering, Operations, and Customer Success is indispensable.

It helped me gain incredible insights and comprehend the importance of each and every role in…

Image by author

Machine learning is an application of artificial intelligence (AI) that provides systems with the ability to automatically learn and improve from experience without being explicitly programmed.

It's easy to define Machine Learning based on the definition mentioned above but it raises further questions like ‘How it's done?’, ‘What are various sub-domains of ML?’, ‘What are various algorithms?’, ‘Do I need to know maths?’, ‘What are various industrial applications?’, etc. Moreover, working in the industry for the past few years, I have realized that as applied scientists we majorly focus on existing concepts and application-level knowledge of ML together with other…

According to scientist and photographer Dr. Roger Clark, the resolution of the human eye is 576 megapixels. That’s huge when you compare it to the 12 megapixels of an iPhone 7’s camera.

^ This makes the human eye highly sensitive to light, enabling us to observe minute details visually. Moreover, humans can detect colors easily since they learn the mapping of various light intensities with their corresponding color names since childhood.

Interestingly, scientists have determined that in the lab we can see about 1,000 levels of dark-light and about 100 levels each of red-green and yellow-blue. So that’s about 10…

Source: Eurekasoft.com via Google Images

Amazon SVP: Exactly how much money are you willing to invest in Kindle?

Jeff Bezos: How much money do we have?

The above lines from one of my favorite chapters — “Kindle” are so powerful and inspiring and depict critical long-term thinking and patience which are exactly the ingredients required for success.

After reading the book “Working Backwards” by Colin Bryan and Bill Carr which highlights various inside stories from Amazon, my biggest takeaway would be — World-class products are built with long-term thinking, always keeping customer’s interests at the top.

Out of tons of learning, I gathered from the…

Image (by Author): Sample wave-plot for various emotions and its corresponding MFCC features

With an increase in the human-computer interaction systems and voice-enabled applications in the contemporary world, it has become indispensable for our intelligent systems to learn recognition of different emotions for much more effective communication. There is an increasing demand to not only extract the linguistic information from the speech but to also incorporate the emotions associated with it.

Speech Emotions Recognition (SER) is a very challenging task because of the huge investment involved in generating appropriate training data and high subjectivity in annotations. For various industrial applications, sometimes it’s not even feasible to generate training data artificially because of the…

With the introduction of a wide range of pre-trained models trained on humongous data, the success of Machine learning in industrial applications has grown exponentially. While we can easily utilize these models by transfer learning either as feature extractors or by fine-tuning on our specific dataset, but generally the performance isn’t great if the pattern is significantly different from the data on which these models are originally trained.

Especially in the case of Natural Language Processing, there are many patterns specific to the data which often reduces the applicability of pre-trained models. …

Due to its potential to improve our lives with abundant possibilities, Artificial Intelligence is becoming an indispensable part of every industry. Although, getting AI-powered may seem attractive for a company; it’s the combination of a) great thoughts, b) discoveries, c) patience and d) the ability to “get shit done” that makes it a reality.

At Squad, we are revolutionizing content moderation in online classifieds and marketplaces. We help provide a balance between approving recently uploaded user-generated listings quickly to the site and maintaining a high standard of the listing quality. …

Ved Vasu Sharma

Data Scientist @ SquadStack | Building AI-driven products https://www.linkedin.com/in/vedvasu/

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