In this video, we will be taking a look at prompt engineering, the hottest new skill in the AI town. We will first take a look at the definition of prompt engineering and then go further into the different techniques like few shot prompting, CoT or Chain of Thought prompting etc. We will also briefly look at RAGs or Retrieval Augmented Generation, which have been driving a lot of use-cases at many companies. Finally, we will end with some tips to devise and create prompts. Happy watching and happy prompting!

Have you ever come across those moving bars that keep going up and down as time goes and wondered if you could make them yourself? If yes, then this video will help you make such a visualization quickly using Python. In this video, we will take a sample dataset from Kaggle (https://www.kaggle.com/datasets/ulrikthygepedersen/life-expectancy) and build the Bar Chart Race visualization using the bar_chart_race Python package. Please do like the video and subscribe to the channel for more such content!

Data Science projects are unlike typical software engineering projects. They have a different stages and also, in many cases, not linearly defined. In this video, I take you through one framework that will help organize your thinking about approaching Data Science projects and provide you guidelines on the different stages in the life-cycle of a Data Science project. If you enjoyed the video, then please don't forget to like, comment and share the video. And yes, please do subscribe to the channel for more such videos!

Have you ever wanted to build your own AI generation tool? If yes, then this video is for you! In this video, I take you through aitextgen, a robust Python tool for text based AI training and generation using GPT-2 or GPT-3 (EleutherAI's open sourced GPT-Neo version which aims to reproduce OpenAI's GPT-3). In the video, I take you through using the pre-trained GPT-2 model to generate texts with your own prompts. We also go through using a custom dataset (Indian news headlines dataset from Kaggle) to finetune a model to generate text as per your custom dataset. If you found this video useful, please do like, share and subscribe to the channel!

In this video, I introduce feature engineering and then take you through the basics of feature engineering for tabular data. Different kinds of data have different feature engineering techniques. Not only that, feature engineering techniques depend on the model you use and the task you are trying to solve. In this video, we look at the different techniques you can use to engineer features for both numerical and categorical datasets. If you find the video informative, then please do like and share it! And don't forget to subscribe to the channel for more such videos!

In this video, I will take you through an introduction to what features mean and where Feature Engineering takes place in the process of the development of a Machine Learning system. I explain, with an example, how features differ from data and how Feature Engineering is dependent on multiple different factors. If you enjoyed watching this video, then please don't forget to like, share and subscribe to the channel!

Shadab leads a team of applied scientists and engineers at G42 to solve problems in healthcare AI. His team develops solutions for clinical care, healthcare operations, and healthcare finance by analyzing structured and unstructured datasets ranging from electronic health records, genomics, medical imaging, and claims, among others. Before joining G42 Healthcare, Shadab was a researcher at the Inception Institute of AI in UAE, where he focused on machine learning from limited data. Shadab obtained his Ph.D. from Dartmouth College in Biomedical Engineering and did a research fellowship at Harvard Medical School and Boston Children's Hospital in Radiology. In this fireside chat, we'll get to know more about his experiences and learnings while building AI systems in Healthcare. We first understand his motivation to work at the intersection of AI and Healthcare and then understand some of the problems he faced while building AI systems and how he overcame them. Towards the end, we will talk to him on some advice he would like to share with upcoming Data and AI scientists.

Machine Learning model interpretation has been increasingly becoming more and more important as ML systems adopt more opaque algorithms and techniques. In this paper (https://arxiv.org/pdf/2007.04131.pdf), Christoph Molnar and a team of researchers take a look at the different pitfalls of using these model agnostic interpretation for machine learning models. We go through the 8 different pitfalls mentioned in the paper and their possible solutions as well. Hope you like this video and if you do, then please like, share and comment on the video. And also subscribe to the channel for more such videos!

MLOps or Machine Learning Operations is gaining more and more importance these days. As models are being increasingly deployed in production, there's an entire ML life-cycle that needs to be taken care of. And this is where MLOps comes into picture. However, often times, many people make mistakes while building and deploying a ML system. In this video, we go through a recently popular research paper (https://arxiv.org/abs/2107.00079) that identified 9 of these antipatterns to avoid while working with ML systems. If you liked this video, please do give it a thumbs up and subscribe to the channel for more interesting videos!

Facebook AI's wav2vec 2.0 is a new framework that claims to perform Automatic Speech Recognition without using a language model. In this video we will quickly take a look at the abstract of the paper and then move on to the implementation of this system using Huggingface. Huggingface provides us with wav2vec2-base-960h model that can be used to perform ASR. As described in the video, here are the relevant links: 1. Link to the paper - https://arxiv.org/abs/2006.11477 2. Link to Huggingface's wave2vec 2.0 model page - https://huggingface.co/facebook/wav2vec2-base-960h 3. Link to the Colab notebook - https://colab.research.google.com/drive/1dnNrGy1U260L403OuhTsDjBQkdGHmvL9

Data Scientists often have multiple hats to wear. One hat they wear sometimes is that of a Data Analyst. In this video, I briefly take you through the six types of data analysis you might encounter in your work as a Data Scientist. If you liked the video, please give it a thumbs up and don't forget to subscribe to the channel.

In this episode of the Fireside Chat, we have Mirza Rahim Baig, Lead Analyst at Zalando SE. He earlier worked as Analytics Lead at Flipkart. Before that he was an electronics engineer before making a transition to Data Science and Analytics. He's a published author and an educator as well. In this chat, we discuss how business problems can be identified, framed and solved and how important it is to have the right frameworks for formulating business problems and solutions. Rahim draws from his 10+ years of experience in the field and shares examples that highlight the importance of problem solving. Finally, we talk about his career transition and his advice for people entering the field of Data Science and Analytics.

Google sheets is one of the most widely used spreadsheet software in the world today. For Data Scientists and other people working with data, it can also be a great source of data. But how does one write data to the sheet programmatically? Enter Python and its libraries (gspread, pandas etc). In this video, I take you through the process of using Python to start writing to your google sheets programmatically and modifying them. As a pre-watch, I'd recommend you to watch the first part of this series, where I introduced how to set things up and read from your gsheets. Here's the link to the first part: https://www.youtube.com/watch?v=rPV9sJQCqr0 Hope this helps you get an idea as to how you can access your data in your gsheet using Python. If you liked the video, please don't forget to like, share and subscribe to the channel.

Google sheets is one of the most widely used spreadsheet software in the world today. For Data Scientists and other people working with data, it can also be a great source of data. But how does one access data from the sheet programmatically? Enter Python and its libraries (gspread, pandas etc). In this video, I take you through the process of using Python to start reading your google sheets programmatically and modifying them. Hope this helps you get an idea as to how you can access your data in your gsheet using Python. If you liked the video, please don't forget to like, share and subscribe to the channel. Link to gspread's documentation: https://docs.gspread.org/en/latest/

How do we go about creating an Anomaly Detection System? One way is to create a rule based system that identifies anomalies based on certain rules. But how does one define these set of rules? Find out in this video. If you liked this video, please don't forget to like, share and subscribe to the channel.