Human Stories in AI: Achal Dixit
Вставка
- Опубліковано 2 бер 2024
- In this episode we have special guest Achal Dixit, a Data Scientist at Delhivery, the largest fully integrated logistics services in India. Achal solves problems using Data, statistics, and machine learning with a focus on business and people. Before Delhivery, Achal was a Business Technology Analyst at ZS. And before that, Achal was a research assistant at Imperial College London.
If you'd like to support StatQuest, please consider...
Patreon: / statquest
...or...
UA-cam Membership: / @statquest
...buying my book, a study guide, a t-shirt or hoodie, or a song from the StatQuest store...
statquest.org/statquest-store/
...or just donating to StatQuest!
paypal: www.paypal.me/statquest
venmo: @JoshStarmer
Lastly, if you want to keep up with me as I research and create new StatQuests, follow me on twitter:
/ joshuastarmer
#StatQuest
To learn more about Lightning: lightning.ai/?
Or just get started with a cool Lightning Studio tutorial: lightning.ai/lightning-ai/studios/the-easiest-way-to-use-gpus-in-the-cloud?
Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/
"People are more obsessed with the methodology/outcome rather than the impact it makes" -Bam josh!
bam! :)
Awesome content...keep it up... we need more podcasts like this.
More to come!
Very nice Achal, kee it up
Bam!
Very nice Achal .keep it up.
bam!
Thank you so much for sharing this with us on UA-cam ❤️🔥 from SeoulNatU
My pleasure 😊!
Lol.
16:30 The trademark lines come out quite naturally.
Turns out “bam” and quest aren’t Josh’s lines. They are statistical terms. :p
:)
Superrrb Awesome Fantastic video
Thanks 🤗
Nice story :D
Yes! It's super cool!
I have recently started refreshing my Machine Learning skills and I have been following your StatQuest videos on UA-cam. I also purchased your book. I found both the videos and the book extremely helpful and easy to understand. Thank you so much for providing these invaluable resources. You have made Machine Learning fun.
I have a question regarding Backpropagation for Neural Networks when we use the sigmoid activation function. I have trouble calculating the derivative of the cross-entropy loss function with respect to W1. The derivative I get following your video on the chain rule is dE/dW = -(y - sigma(W1x1 + W2X2 +b))x, but I have also seen people doing it as -(y - y_out) *sigma(W1x1 + W2X2 +b) * (1 -sigma(W1x1 + W2X2 +b)) * x. I'm confused as to which one is correct.
I know you are busy, so my apologies for taking your time. Any help from you will be greatly appreciated.
Thank you so much in advance.
Unfortunately I'm too busy right now to give you a good answer.
@@statquest Thanks for getting back to me, but I have to say, I'm feeling pretty disheartened by the lack of support and kindness in your reply. I've been a fan of your content, subscribed to your channel, and even bought your book, so I was hoping for a warmer and more helpful response. Even a little hint or gesture would've been nice. Anyway, I'll just keep looking for help elsewhere. Thanks for your time.
@@user-qm4eb5ro4y I sorry I can't help you more. I do the best I can, but today is a super busy day.
hi, i love your video so much,!they explain neural networks clearly, they help me a lot in my study. so can i translate your video to chinese and publish it on chinese site. is there any way i can contact with you so we can discuss this. thank you and your videos, they did help me in understanding !
Thank you! I'm already working on a bilibili channel. Search for StatQuest on it and check it out.
I get it. Can I join your bilibili channel and do some translation work?@@statquest
🎉🎉🎉🎉🎉
Bam!!!
14:40 "Metric makes us visualize data in a linear scale. But those people do not lie on a linear scale". I don't get the point.
Are you sure that is the correct time point?
@@statquest fixed it. 👍🏻
A singular metric for n people can be seen as an array of n data points. So for that metric people between values let's say 40-50 transition from class A to B, given class A is 50. The individual metric forces an assumption of this linear understanding of classification. Meanwhile, in the actual problem statement you cannot classify someone between 40-50. A person at 41 can be in class B or 49 can be in class A. :)
Hope this helps. The metric is linear but the behaviour of petients in between is not!
We want yolov8
noted!
@@statquest 1000th time😂😂
@@vigneshvicky6720 Please know that I work as hard as I can and I do my best, but I'm slow. Making videos takes me forever. I have noted, many times, that you want me to cover this topic. Unfortunately that is the best I can do right now.
@@statquestit might take some time to develop, but it is amazing content always!
Indians have been summoned. Maharashtrians, even more so 🚩
:)
Dixits are not only Maharashtrians lol, they are lot of them in Karnataka too
Please. Dont do these here.
first
bam!
what the heck?
I have a lot of content that describes how ai work in theory, this podacast is an attempt to also describe how it is used in practice.
@@statquest er...does you tube keep auto deleting my posts about your sponsor or are you doing that?
@@tonywillingham8109 I'm not deleting your comments. So maybe youtube's filters are doing something to them.