himanshu (@himarora) header
himanshu (@himarora) profile picture
Joined April 2007
Photo by himanshu (@himarora)Photo by himanshu (@himarora)Photo by himanshu (@himarora)
Replying to @zomatocare
@zomatocare you need to train your staff. Is this how they deliver ? He just ran away. – at Mumbai, India
1
1
2
@zomato Please look into – at Mumbai, India
2
1
Some advice I give my graduate students about how to keep on top of the literature in their field. A 🧵: 1/
119
1,515
147
7,870
This is incredible stuff from #deepmind – at Panvel, India
Since 1969 Strassen’s algorithm has famously stood as the fastest way to multiply 2 matrices - but with #AlphaTensor we’ve found a new algorithm that’s faster, with potential to improve efficiency by 10-20% across trillions of calculations per day! dpmd.ai/dm-alpha-tensor
1
Below is an example of a problem #AlphaCode can successfully solve, using the exact information seen on @codeforces, & the program that #AlphaCode writes. By @liyuajia, David Choi, @junyoungch, @NateKushman, @Mononofu, @RemiLeblond, Tom Eccles, James Keeling, @FelixAxelGimeno 2/
40
464
221
1,659
Replying to @iamokariya
@amokariya Hi I know you are not the righr person to ask this. But I am really pissed off. I shipped a courier with tracking number 21007200075917 for malur Bangalore, it was for overnight shipping. I paid 600/ for that. I booked it on 28-06-2021. It has still not reached.
1
Your customer care never picks up any call. Please check.
1
1
@amokariya I have even mailed to your customer care as well as tweeted @maruti_courier . But no response.
1
Replying to @ICICILombard
@ICICILombard pathetic service from your surveyor Shrirang shinde. I am paying car insurance from last 9 years. I have paid 1 lakh 20 k in premium. And the first time I go for claim . He is making excuses , that my damage is older and you cannot claim it .
2
It's hardly a matter of 5-6k still your people are harassing us. Requesting senior management to interfere. In corona times no body can come for a body work.
Double descent is not a violation of Bias Variance Tradeoff. Very well explained. Thanks @daniela_witten
The Bias-Variance Trade-Off & "DOUBLE DESCENT" 🧵 Remember the bias-variance trade-off? It says that models perform well for an "intermediate level of flexibility". You've seen the picture of the U-shape test error curve. We try to hit the "sweet spot" of flexibility. 1/🧵
1
2
Salute !!
This Post is from a suspended account. Learn more
@RNTata2000 Sir, we have created BaggageAI (baggageai.com), for automatic detection of contraband in X-Ray images of scanned bags. It can be deployed at Airports, hotels, offices etc. We can deploy it at one of your TCS offices also just for demonstration.
1
3
We have tested it at Pune Airport as well. Looking forward to work with you. Thanks, Himanshu Arora
1
Upskill while others are complaining about a pandemic they have no control over. Take control of your time with Dimensionless. #MondayMotivation . . . #DataScience #LearnDataScience #MachineLearning #Statistics #DataScienceTraining visit us at dimensionless.in
The demand for data scientists is not abating-even during these challenging times. This shows how much all organizations across all sectors rely upon data science. . Issued in Public Interest. . . . #Social_Distancing #DataScience #AI #ML #LearnDataScience #Public_Interest
2
1
Very well written
This quoted post is unavailable.
himanshu retweeted
You don't know what pain is until you've tried to install an older version of CUDA
33
59
11
813
Hyperparameter tuning is a big problem in neural networks. #keras team has recently launched keras tuner for that. Thanks @fchollet
One of the projects we released recently: Keras Tuner. A dedicated framework for hyperparameter tuning for Keras models keras-team.github.io/keras-t…
Popularity of keras as a goto tool for DL is increasing day by day.
We often talk about how Keras makes DL more accessible and easier to use, and how this helps beginners. But those who stand to benefit most from good UX *aren't* the beginners. It's actually the very best DL people in the world.