Shows
mbanerjeepalmer+listennotes 's Listen LaterRecSys at Spotify // Sanket Gupta // #232 Podcast: MLOps.community (LS 35 · TOP 3% what is this?)Episode: RecSys at Spotify // Sanket Gupta // #232Pub date: 2024-05-16Get Podcast Transcript →powered by Listen411 - fast audio-to-text and summarizationJoin us at our first in-person conference on June 25, all about AI Quality: https://www.aiqualityconference.com/Sanket works as a Senior Machine Learning Engineer at Spotify, working on building end-to-end audio recommender systems. Models built by his team are used across Spotify in many different products, including Discover Weekly and Autoplay.M...
2025-09-1750 min
MLOps.communityNavigating the AI Frontier: The Power of Synthetic Data and Agent Evaluations in LLM Development // Boris Selitser // #241Join us at our first in-person conference on June 25, all about AI Quality: https://www.aiqualityconference.com/Navigating the AI Frontier: The Power of Synthetic Data and Agent Evaluations in LLM Development // MLOps podcast #241 with Boris Selitser, Co-Founder and CTO/CPO of Okareo.A big thank you to LatticeFlow for sponsoring this episode! LatticeFlow - https://latticeflow.ai/// AbstractExplore the evolving landscape of building LLM applications, focusing on the critical roles of synthetic data and agent evaluations. Discover how synthetic data...
2024-06-1857 min
MLOps.communityFrom Robotics to Recommender Systems // Miguel Fierro // #240Join us at our first in-person conference on June 25, all about AI Quality: https://www.aiqualityconference.com/Miguel Fierro is a Principal Data Science Manager at Microsoft and holds a PhD in robotics.From Robotics to Recommender Systems // MLOps Podcast #240 with Miguel Fierro, Principal Data Science Manager at Microsoft.Huge thank you to Zilliz for sponsoring this episode. Zilliz - https://zilliz.com/.// AbstractMiguel explains the limitations and considerations of applying ML in robotics, contrasting its use against traditional control methods that...
2024-06-1158 min
MLOps.communityRecSys at Spotify // Sanket Gupta // #232Join us at our first in-person conference on June 25, all about AI Quality: https://www.aiqualityconference.com/Sanket works as a Senior Machine Learning Engineer at Spotify, working on building end-to-end audio recommender systems. Models built by his team are used across Spotify in many different products, including Discover Weekly and Autoplay.MLOps podcast #232 with Sanket Gupta, Senior Machine Learning Engineer at Spotify // RecSys at Spotify.A big thank you to LatticeFlow for sponsoring this episode!// Abstract...
2024-05-1650 min
T.A.G.S (The Abhinav Gupta Show)Exploring Salesforce Startup Program with Sanket Atal and Ankit AroraIn this conversation, Sanket Atal, Managing Director for Salesforce Operations in India, discusses the Salesforce Startup Program and its goal of supporting startups in India. The program is not an accelerator or incubator but a startup community that offers connections, guidance, and access to the Salesforce platform. Sanket shares examples of startups that have benefited from the program, including developing apps, connecting with sales, and achieving success in the Salesforce ecosystem. The program promotes a pay-it-forward model, where startups help each other and contribute to the community. Salesforce is an accessible ecosystem to enter, even without a technical background...
2024-03-1936 min
Choosing Leadership with Sumit GuptaLeadership Journeys [107] - Sanket Nadhani - "A sabbatical helped me discover myself, build confidence, and open my mind"This is the Leadership Journey series on the Choosing Leadership Podcast.I believe we all have a lot to learn from each other's stories - of where we started, where we are now, and our successes and struggles on the way. With this series of interviews, my attempt is to give leaders an opportunity to share their stories and for all of us to learn from their generous sharing. If you know a leader whom you would like to see celebrated on the show, please send me a message on LinkedIn with their name.Join...
2023-08-0725 min
Behind The WicketsIs IPL bad for Indian Cricket?A lot of blame was put on #IPL for India's #wtc2023 debacle. Today we discuss if IPL is really that bad for Indian cricket or has it churned out enough match winners which has made India a better team than in the past? Is IPL a boon or a bane for Indian Cricket?We would love to know you views in the comment section.Tweet or comment using #askbtw to get your comments featured in our videosFollow us on socials for more fun stuff.
2023-06-1927 min
Yannic Kilcher Videos (Audio Only)ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning (Paper Explained)#ext5 #transferlearning #exmix
The T5 model has been a staple for NLP research for the last years. Both its size and its approach to formulate all NLP tasks as prompt-based language modeling make it a convenient choice to tackle new challenges and provides a strong baseline for most current datasets. ExT5 pushes T5 to its limits by pre-training not only on self-supervised mask filling, but also at the same time on 107 different supervised NLP tasks, which is their new ExMix dataset. The resulting model compares very favorably to T5 when fine-tuned to downstream tasks.
2021-12-0140 min
The Data Life Podcast27: Building Open Source Data Startup with Airbyte CEO, Michel TricotWe talk with Michel Tricot, who is the Founder and CEO of Airbyte, which is an open source data integration Y Combinator startup. It has raised over $30M in capital and has been growing quite fast. It was a great conversation and I think you will also enjoy it. 🎉We cover lots of things in the podcast including: 1. Technical aspects of what Airbyte does, how it sits in the ETL/ ELT landscape, how it differs from other tools such as Fivetran, Stich etc. 2. Data Warehouses being a canonical source of data and how Airby...
2021-10-1144 min
ThyDoc HealthKidney Kharab hone Ke Lakshan, Kidney Failure Symptoms, Kidney Kharab hone ke Sanket, ThyDocHealthWe will discuss the symptoms of kidney failure. Symptoms of kidney failure - 1)Fatigue -The patient feels tired all the time. This is because of reduced production of erythropoietin when the kidney fails, which results in reduced production of red blood cells causing a decrease in the amount of hemoglobulin in blood, a condition which is also known as anemia. Accumulation of body toxins is also the reason for this. 2) Difficulty in breathing-This occurs because of the accumulation of extra water in the lungs due to which enough oxygen does not reach the body organs and another reason for...
2021-09-0308 min
The Data Life Podcast26: Building Data Engineering Pipelines at Scale (with Data Warehouse, Spark and Airflow)Imagine you are at a beach and you are hanging out and seeing all the waves come and go and all the shells on the beach. And you get an idea. How about you collect these shells and make necklaces to sell? Well how would you go about doing this? Maybe you’d collect a few shells and make a small necklace and try to show to your friend. This is where we begin our journey on learning about data engineering pipelines. Using an example of running a necklace business from shells - we learn about the foll...
2021-08-1839 minThe Data Life Podcast25: Talking Data Privacy with Jeff BermantIn this episode, I'm excited to be talking with Jeff Bermant, who is the founder and CEO of Cocoon Mydata Rewards browser. It is a browser based off Chrome and it pays people to use it! ✨ In this episode we talk about data ethics and privacy, and how Jeff believes that users should be paid for their data. We talk about GDPR and similar laws in US, future of data privacy and more! Go to https://getcocoon.com to download and use Cocoon Rewards Browser. ~Thanks for listening~--- Send in a voice...
2021-08-0428 min
My Startup PodcastINR 499 crore support announced by Defence Ministry for Startups and MSMEsIn order to financially support startups and MSME, individual Innovations and Partner Incubations, the Defence Ministry has announced a support of Rs.498.8 in the defence sector.Apart from finding available slots, users can now book Covid- 19 vaccination slots on the Paytm app. The slots can be booked for both, Covaxin and Covishield in the nearest centres.Abu Dhabi's sovereign fund ADQ is in talks with e-commerce giant Flipkart in order to invest 500 million dollars in the company as it raises funds ahead of a potential Initial Public Offering next year.Indian Space Research Organisation has launched three new online...
2021-06-1603 minThe Data Life Podcast24: Promoting Women in Tech - With Rupal GuptaIn this episode, we are talking about women in tech with Rupal Gupta. Rupal, a recent graduate from Online MS in CS from Georgia Tech, is a data engineer in the industry and is passionate to help promote women in tech. She also has some great tips and resources for anyone trying to break into data science and tech!
In this episode we talk about things that can help promote women in tech, women in tech conferences such as Grace Hopper, looking for jobs, resources to prepare for the interviews etc.
If you...
2020-10-0800 minThe Data Life Podcast23: 10 Reasons Amazon SageMaker is great for ML Model DevelopmentIn this episode, we talk about what makes Amazon SageMaker great for ML model development including model building, training and deployment. We cover 3 advantages in each of these 3 areas.
We cover points such as:
1. Host ML endpoints for deploying models to thousands or millions of users.
2. Saving costs for model training using SageMaker.
3. Use CloudWatch logs with SageMaker endpoints to debug ML models.
4. Use preconfigured environments or models provided by AWS.
5. Automatically save model artifacts in AWS S3 as you train in SageMaker.
6. Use of version control...
2020-06-1721 min
OverllookedEP.6 | Akshay Gupta on running the biggest pet festival | Overllooked with Pooja AdvaniThe man behind the biggest pet festival in India, Akshay Gupta, tells us why he does not have a pet of his own.
link to video version : https://bit.ly/3gMSyoL
A Frozen Time Production original series
Credits : Produced by Frozen Time Production
Producer : Pooja Advani
Executive Producer : Sanket Deorukhkar
Director : Sanket Deorukhkar
Concept : Sanket Deorukhkar
Cinematographer : Gufran Khan, Riya Coutinho, Sanket Deorukhkar, Tia Shivpuri
Editor & Colorist : Riya Coutinho
Sound/Music & Background score : Mo...
2020-06-0140 minThe Data Life Podcast22: Transfer Learning for NLP - With Paul AzunreIn this episode, we are talking with Paul Azunre. Paul is one of the world’s experts in the area of Transfer Learning for NLP and is also an author of the upcoming book Transfer Learning for NLP published by Manning Publications. In this episode we talk about things such as:
1) Paul’s background and how his background in maths and optimization as well as fake news detection got him started in transfer learning in NLP.
2) How Paul got started with the book, book writing process as well as tips to the listeners for writing a te...
2020-04-1348 minThe Data Life Podcast21: Why Scikit-Learn and Keras are Awesome for MLIn this episode, we talk about why the two libraries Scikit-Learn and Keras are great for machine learning. These two libraries combined with Pandas form the 3 core libraries in Python for a data scientist today.
We cover things like:
1) Data Exploration and data cleaning - how Pandas and Jupyter notebooks provide a good way to get started here.
2) Data Transformation - how Scikit-Learn provides many useful functions like train_test_split, Scalers, PCA etc.
3) Data Fitting - how Scikit-Learn provides good shallow models and Keras provides great support to quickly get...
2020-01-2621 minThe Data Life Podcast20: Yogi's Guide to Analytics - An Interview with Akshay KanadeIn this episode, we talk with Akshay Kanade. He is a business analyst working in New York City who likes taking a big view of data, and has very interesting spiritual views on data analytics and life in general, he is also a handwriting expert- he can read people’s handwriting and can recognize a lot about their personalities.
In this interview we will cover several things such as:
- How has been an analyst influenced Akshay's life?
- Introspection about data and analytics
- Taking high level view of data - co...
2019-12-0137 minThe Data Life Podcast19: What makes a Good Data Scientist? - An Interview with Patrick McCloryIn this podcast episode, we do an interview! We talk with Patrick McClory, who is the founder and CEO of IntrospectData. He is an expert working in areas of data science consulting, large machine learning projects, math, statistics and more.
In this episode we cover several interesting topics such as:
1) What makes a good data scientist?
2) The different roles in the industry such as data engineer, machine learning engineer, data analyst etc.
3) The first mile problem: Data ownership and ethics of data collection.
Patrick can be reached at patrick@introspectdata.com and...
2019-11-2258 minThe Data Life Podcast18: 5 Things to Consider for Master of Science (MS) in USWhat should you consider for pursuing MS in US? There might be several questions in your mind as you explore this question. In this episode we cover some of the main things to consider before you make the decision. I also go into details about things which I wish I knew before coming to US for MS.
The things I cover in the podcast are to consider for MS in US are:
1) Location matter more than rankings.
2) Talk to professors before applying.
3) Culture of hard work, and advantage of having...
2019-11-1520 minThe Data Life Podcast17: Why Pandas is the new ExcelThe Data Life Podcast is a podcast where we talk all-about real life experiences with data and data science science tools, techniques, models and personalities.
In this episode, we will talk about how Pandas is becoming a tool of choice for many data scientists for doing their data analysis work. We will explore how Pandas wins over Excel in several key areas that are important for businesses today:
1) Large dataset sizes
2) Different kinds of input formats such as JSON, CSV, HTML, SQL etc
3) Complex business logic
4) Linking data analysis work to...
2019-10-2518 minThe Data Life Podcast16: Getting Started with Natural Language ProcessingSo many tweets and news articles and unstructured text surrounds us. How do we make sense of all of these? Natural language processing or NLP can help. NLP refers to algorithms that process, understand and generate aspects of natural language either in text or in spoken voice. In this episode we will cover some of the common techniques in NLP to help get started in this exciting field!
We cover several tasks in a NLP pipeline:
1. Tokenization and punctuation removal
2. Stemming and Lemmatization
3. One hot vectors
4. Word embeddings including Word2Vec and...
2019-10-0521 minThe Data Life Podcast15: Using Flask, REST API and Vue.js to build a Single Page Web ApplicationAs a data scientist, you will work on machine learning models that are deployed on websites - usually wrapped around a REST API, these days they also call this approach a “micro-service”. It is for this reason it is important to know how backends and front ends work and how to build them. In this episode, we talk about building a note app which is a Single Page Application or SPA using Pythons flask library for backend and Vue.js for frontend. We use REST API to communicate between them.
We cover following topics in Q and...
2019-09-1622 minThe Data Life Podcast14: Building a Character-Based Text ClassifierEver wonder how to automatically detect language from a script? How does Google do it?
Ever wonder how Amazon knows whether you are searching for a product or a SKU on its search bar?
We look into character-based text classifiers in this episode. We cover 2 types of models. First is the bag-of-words models such as Naive Bayes, logistic regression and vanilla neural network. Second we cover sequence models such as LSTMs and how to prepare your characters for the LSTMs including things like one-hot encoding, padding, creating character embeddings and then feeding these...
2019-08-0725 minThe Data Life Podcast13: Statistics of A/B TestingYou and your team might spend a lot of time building a new feature. But how do you know if this feature will be liked by the users? One of the ways to statistically prove this is by using A/B testing. Listen to this episode to get tips, tricks and intuition behind hypothesis testing, alpha, beta, p-values, two-sample t-tests and more.
These understandings have been learnt from experiences deploying A/B tests in the field, and talking to experts.
These ideas are typically not covered in traditional A/B testing texts which...
2019-07-1723 minThe Data Life Podcast12: The importance of business impact in data scienceIn this episode, we will talk about the importance of business impact in data science. "Your users don't care how smart you are" was a quote I read that got me started in thinking about this.
The right way to do data science is to think of users, revenue impact, business value and go for the simplest solution possible. The wrong way to do data science is to just find a nail to hit the hammer with rather than the other way around.
We will cover about all this and more...
2019-06-2605 minThe Data Life Podcast11: The Ten Essential Machine Learning QuestionsThis episode covers the ten essential machine learning questions. Disclaimer: Baseline answers have been provided in the episode for guidance. For complete accuracy, please refer to textbooks or to courses by Andrew Ng on Coursera.
If this content is useful, please consider buying me a coffee via the link https://anchor.fm/the-data-life-podcast/support
Resources:
1. Machine Learning Course by Andrew Ng: https://www.coursera.org/learn/machine-learning
2. Deep Learning Course by Andrew Ng: https://www.coursera.org/specializations/deep-learning
Questions:
1. What is underfitting and overfitting? How to avoid...
2019-06-2120 minThe Data Life PodcastMining Twitter Data for Sentiment Analysis of EventsTwitter is a rich source of live information. Is it possible to run sentiment analysis on what the world is thinking as an event unfolds over time? Could we track Twitter data and see if it correlates to news that affects stock market movements? These are some of the questions that we will answer in this podcast episode.
There are 6 steps for mining Twitter data for sentiment analysis of events that we will cover:
1) Get Twitter API Credentials
2) Setup API Credentials in Python
3) Get Tweet Data via Streaming API using Tweepy
4...
2019-06-0120 minThe Data Life PodcastDon't Be Shy To Pursue Your InterestIn this episode, we will talk about things like Maslow's Hierarchy of Needs, and focussing on higher level needs such as satisfaction and achieving full potential. In the area of tech, data science and software development, admitting your interest could involve "shyness" as the next shiny cool thing is pursued by everyone. But if your interest is in a niche, don't let others stop you from putting in an effort to become great at it.
Thanks for listening, and please show your support to keep this podcast going!
---
Send in a voice message...
2019-05-1906 minThe Data Life PodcastReview of Udacity Nanodegrees - are they worth it?Udacity has become a popular platform for learning about various things in data science, machine learning and programming in general. In this episode, we will discuss the good, bad and ugly of the Udacity nanodegrees. I will also cover my experiences with Deep Learning and NLP Nanodegrees.
We will cover things like how Udacity has great production quality and has nice intro courses, but due to their lack of depth and low community engagement, the high costs might not be justified (most of their nanodegrees are around $1,000 currently) But if cost is not a concern, then...
2019-05-0314 minThe Data Life Podcast6 Steps to Transition to Data Science from non-CS backgroundIn this episode we will talk all about the various steps to transition to data science from non computer science backgrounds.
One of the main difficulties people face from non-CS backgrounds is how overwhelming it can be to transition to data science field, I talk about my own journey, and share the 6 steps which can help you in your own data science career!
00:00 to 02:10: Introduction
02:11 to 06:00: My Background of moving to data science from electrical engineering
06:01 to 10:56: Steps 1 to 3 covering things like using external APIs, already processed datasets and performing full...
2019-04-2117 minThe Data Life PodcastThe Top 5 Data Science PodcastsWelcome! In this episode, we will cover some of the top data science podcasts, that have helped me a lot in my own journey, and hopefully will be helpful to you as well.
The top 5 podcasts are (linked to my favorite episodes):
1) AI in Industry with Daniel Faggella
2) This week in Machine Learning and AI (TWiML)
3) DataFramed
4) Data Skeptic
5) Talk Python to Me
Listen to the episode for the sixth bonus podcast!
If you think I should mention another podcast here, let me know and I...
2019-04-1010 minThe Data Life Podcast3 Lessons I Learnt building a Video CourseHave you ever thought about building a video course? Have you wanted to share your expertise with other people via a video course on different platforms like Udemy? Have you wondered what are the economics and revenue details of building a course? This podcast episode is for you!
In this episode, I talk about my experience in building my first data science video course, lessons learnt and how you can use these in your own video course.
00:00 to 09:30- I talk about my experience with Packt Publishing in developing the video course.
2019-03-3020 minThe Data Life PodcastOverview of Netflix and Spotify like recommendation enginesIn this episode, we cover the two main types of recommendation engines used at companies like Netflix and Spotify.
1) Content based recommendation systems use the genres or tags of each product to find other similar products to recommend to users.
2) Collaborative filtering based recommendation systems use user activity and user ratings on the website to recommend products.
We go through the pros and cons of each, the challenges, how do companies like Netflix and Spotify scale their recommendation engines for millions of users and more!
My code in the...
2019-03-2215 minThe Data Life Podcast3 Mistakes to Avoid in a Machine Learning ProjectYou and your team might spend weeks or even months building a model. These are the 3 mistakes to avoid in your next machine learning project! This can save you a lot of time and effort in your next project.
These tips have been learnt from experiences deploying ML models in production as well as hearing from experts in the field.
These tips and mistakes are typically not covered in traditional machine learning texts and courses, and that's why I really wanted to cover it in this podcast...
2019-03-1512 minThe Data Life PodcastFlask is a Great Tool for Full Stack Data ScienceIn this episode, we will talk all about what makes Flask such a great tool for both beginner and experienced data scientists to know. It was one of the first tools I learnt in my data science journey, and it has been so useful along the way.
Flask is a micro-framework in Python which allows to build websites in a simple way. Flask will make you as a data scientist work better with the front end engineers. Also, it is a great way to build something like say recommender systems where, users can input a product...
2019-03-0512 min
The Data Life PodcastHello, World!To kick things off, I talk about the kind of topics you can expect to hear in this podcast. Welcome to The Data Life!
---
Send in a voice message: https://anchor.fm/the-data-life-podcast/message
Support this podcast: https://anchor.fm/the-data-life-podcast/support
2019-02-1901 min