Lavanya 🐝 @lavanyaai Twitter profile

Pinned Tweet

Lavanya 🐝

3 years

Excited to announce we've raised a Series C at $1 Billion valuation to continue building our developer-first MLOps platform. Checkout this post by @l2k for details: I want to take a moment to thank the people who've made this possible.

6

18

282

Last Seen Profiles

@ynsc212v

@sai_maria0420

@ElijahWebb35

@Aliasgirl

@NutritionEsport

@joseph_kil76192

@sikezy_

@accionables

@MVHoogeveen

@bexturner

@jandakembangstw

@bxllflowersss

@marimo_engineer

@CbCDRUMS

@michael_mwanga

@x_ariix

@up_khormi

@grindtime_dj3

@sammiegroup

@imf0ive97

@kel_rosa_

@Lil_Louie13

@Pecintastw4050

@Javier_VeraRodV

@BurchardtMiles

@weedouthate

@kanavsintern_

@stw_pdg

@DrAnneCarson

@jandakembangstw

@amoregemscom

@yearbook_GYIL

@Emsene01

@mugtmjo

@LAKingsPR

@UNCECL

Lavanya 🐝

@lavanyaai

4 years

We're thrilled to launch Paper Projects – an opportunity to implement, build on top of & apply interesting ML papers. We've picked 9 ML papers for you to creatively explore. You can work in teams or alone. #machinelearning #deeplearning #100daysofmlcode

12

291

1K

Lavanya 🐝

@lavanyaai

4 years

My favorite linear algebra for ML resource is this blog. Mainly because it comes with code, which for me makes the math so much more intuitive! 🙂 The intro to SVD is *chefs kiss*

Deep Learning Book Series · 2.8 Singular Value Decomposition

hadrienj.github.io

sisyphus bar and grill

@itunpredictable

4 years

@lavanyaai Linear algebra for machine learning would be incredibly useful post for a ton of people out there

2

0

14

7

179

857

Lavanya 🐝

@lavanyaai

3 years

Excellent set of class notes for Stanford's CS224 (Machine Learning with Graphs) course by Anil Karaka! If you're looking to get started with Graph Nets, this is a great place to start!

Machine Learning With Graphs.

Class Notes for CS224W (http://web.stanford.edu/class/cs224w/). Made by Anil using Weights & Biases

wandb.ai

3

104

509

Lavanya 🐝

@lavanyaai

5 years

If you wanna know what it takes to be on top of the Kaggle leaderboard, I wrote a kernel you can follow to make it to the top 0.3%. 👩🏼‍💻 #100DaysOfMLCode #MachineLearning #DataScience

How I made top 0.3% on a Kaggle competition

Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources

www.kaggle.com

5

104

477

Lavanya 🐝

@lavanyaai

3 years

6

28

436

Lavanya 🐝

@lavanyaai

4 years

We strongly believe that ML research should be reproducible & accessible to all. So we’re excited to offer support to participants of the Reproducibility Challenge in form of $500 to help with computation costs, & a slack community where you can collaboratively reproduce papers.

6

50

368

Lavanya 🐝

@lavanyaai

3 years

My team is hiring! 👩‍🔬 ML Engineers 👨‍🔬 Project Managers Perks include: working on insanely exciting/challenging problems, on a product ML engineers love, with the smartest/kindest/most fun folks in the world DM me! #deeplearning

6

102

336

Lavanya 🐝

@lavanyaai

3 years

Something that came up today in a convo with friends: It's very difficult to compete with someone who is having fun with their work. You can try to emulate them, but it's hard to do for 12 hour days/weekends. The difference is: to them they are playing & to you you're working.

8

23

334

Lavanya 🐝

@lavanyaai

4 years

Introducing one of our most highly requested features – the Confusion Matrix! You can now log a multi-class CM in one line of code, & compare model predictions across classes. 🪄 Log a confusion matrix in 2 mins #deeplearning #machinelearning

3

47

320

Lavanya 🐝

@lavanyaai

4 years

Totally forgot about this – I have some notes on Machine Learning, linear algebra, stats, data wrangling et all. They might turn out to be useful to some people here. #MachineLearning #DeepLearning #100DaysofMLCode

14

77

315

Lavanya 🐝

@lavanyaai

2 years

Every day when I go to Fully Connected, I'm blown away by the quality of intermediate/advanced deep learning tutorials we're publishing! If you haven't bookmarked it yet, you definitely should! 😊 🐝

1

47

315

Lavanya 🐝

@lavanyaai

5 years

Building a neural network can be confusing! I wrote a guide to help you navigate the treacherous NN waters using @weights_biases 🧜‍♀️ Highly rec forking the kernel & playing with the code! Post: Code: #MachineLearning #DataScience

Training a Neural Network? Start here!

Explore and run machine learning code with Kaggle Notebooks | Using data from No attached data sources

www.kaggle.com

5

90

317

Lavanya 🐝

@lavanyaai

4 years

Deep learning gets all the fancy tools. So we made our friends who scikit a tool to measure & compare your model performance, with one line of code. Try it here: It was such a blast working on this! 😊 #MachineLearning #DataScience #100DaysofMLCode

5

69

284

Lavanya 🐝

@lavanyaai

4 years

Train a neural network to convert an image into a stunning 3D photograph – 📊 Visualize: 📹 2 minute papers video: 📜 Paper: 👩🏼‍💻 Code: #machinelearning #deeplearning #100daysofmlcode

Google Colab Notebook

Run, share, and edit Python notebooks

colab.research.google.com

3

90

284

Lavanya 🐝

@lavanyaai

5 years

I really hope this Siraj revelation incites a collective return to what matters most — technical skill and integrity. We’re here because we’re trying to push the boundaries of machine learning, and build wicked cool things. Less hype around ML is a great thing in my opinion! 🙌🏼

vicki

@vboykis

5 years

In my post on Siraj and how he got to this point on Friday morning, I expressed hope that his livestream was a chance for him to come clean and start over. Welp.

11

39

221

8

33

272

Lavanya 🐝

@lavanyaai

4 years

Visualize your sklearn model performance with just one line of code! 👾 Excited to show you the new @weights_biases sklearn integration. Give it a shot and let me know what you think. #MachineLearning #DataScience #100DaysofMLCode

4

60

259

Lavanya 🐝

@lavanyaai

4 years

If you're looking for ways to tune your HuggingFace #transformer models, these 2 resources might be helpful – 🦊 Step by step guide – 🐋 BERT vs DistilBERT - #machinelearning #deeplearning #100daysofmlcode

A Step-by-Step Guide to Tracking HuggingFace Model Performance

This article provides a quick tutorial for training Natural Language Processing (NLP) models with HuggingFace and visualizing their performance with W&B.

wandb.ai

2

63

258

Lavanya 🐝

@lavanyaai

4 years

I've written a couple of Kaggle kernels over the last year. I think folks here might find these helpful 🐦 Short thread – 1. Getting Started with a competition Understand your dataset inside out + feature engineering #kaggle #machinelearning #datascience

Getting Started with Kaggle: Explore the dataset

Explore and run machine learning code with Kaggle Notebooks | Using data from House Prices - Advanced Regression Techniques

www.kaggle.com

5

36

235

Lavanya 🐝

@lavanyaai

3 years

Join @jeremyphoward & the @weights_biases team for our 1st Fastbook reading session on June 3, 2021 at at 8pm PST / 1pm AEST! Over the next 20 weeks, we'll dive into this hands-on-guide to deep learning. 📍 Register: #deeplearning #machinelearning

5

65

234

Lavanya 🐝

@lavanyaai

4 years

This is a great collection of resources on deep learning, and other subfields including graph neural networks, bayesian deep learning, medical imaging etc.

3

46

236

Lavanya 🐝

@lavanyaai

2 years

Today, we’re so excited to launch V2 of our wonderful community, Fully Connected! FC's mission is simple – to build a shared knowledge base for machine learning in the real world. 🙂 🪄

1

42

228

Lavanya 🐝

@lavanyaai

1 year

We are so excited to launch 2 highly requested features today – Production Monitoring, and the ability to build powerful LLM/ML applications in visual, interactive, and composable way. Check them out here: 🪄 Production Monitoring: 🪄 Weave:

3

42

226

Lavanya 🐝

@lavanyaai

5 years

I'm working on a bunch of Computer Vision blog posts, taking requests for topics! 👩‍🎤 Lineup so far: • Object Tracking using SLAM • Image Captioning with CNN+RNNs • Style Transfer • Face Detection • YOLO detection model • Attention Mechanism #MachineLearning #100DaysOfMLCode

16

25

224

Lavanya 🐝

@lavanyaai

5 years

If you're looking to play with Generative Modelling, David Foster's book is 🔑. You'll learn to build state-of-the-art deep learning models that can paint, write beautiful prose, compose music and play games. #MachineLearning #DataScience #100DaysOfMLCode

0

32

213

Lavanya 🐝

@lavanyaai

3 years

We're thrilled to announce that we just raised $45 million! So proud of the whole W&B team & of @l2k for making this happen. 🥂 We're building a really special product, with really special people and having an insane amount of fun doing it!

Weights & Biases Raises $45M To Build Better Tools for ML Practitioners

In this article, Weights & Biases CEO, Lukas Biewald, gives context to W&B's $45m raise from Insight Partners, and explains his approach and future plans for the company. .

wandb.ai

6

16

212

Lavanya 🐝

@lavanyaai

4 years

Neural networks are notoriously hard debug because the code doesn't crash, raise an exception, or slow down. They simply converge to poor results. @ayushthakur0 shows you how to debug your neural networks! #machinelearning #deeplearning #100daysofmlcode

Visualizing and Debugging Neural Networks with PyTorch and Weights & Biases

In this article, we explore what causes a neural network to underperform. We also discuss the problem of vanishing and exploding gradients, providing some solutions.

wandb.ai

2

50

202

Lavanya 🐝

@lavanyaai

4 years

Great intro to Graph Neural Networks by Yash Kotadia that summarizes the need for GNNs, explains why they're special & analyzes the Gated Graph Convolutional Network architecture which is performant while being scalable. #machinelearning #100daysofmlcode

Part 1 – Introduction to Graph Neural Networks With GatedGCN

This article summarizes the need for Graph Neural Networks and analyzes one particular architecture – the Gated Graph Convolutional Network.

wandb.ai

3

71

201

Lavanya 🐝

@lavanyaai

4 years

A really well done comparison between modern data augmentation techniques for computer vision: ◦ Cutout ◦ Mixup ◦ CutMix ◦ AugMix and their impact of model robustness by @ayushthakur0 . ✍️🏼 Read it here #machinelearning #deeplearning #100daysofmlcode

Modern Data Augmentation Techniques for Computer Vision

This article gives a comparison between Cutout, mixup, CutMix, and AugMix augmentations, and their impact on model robustness. .

wandb.ai

0

47

168

Lavanya 🐝

@lavanyaai

4 years

If you're working on interesting Machine Learning projects and would like to write about them for the @weights_biases blog, DM me! We're always looking for cool people to join the W&B Authors program! ✍️ #MachineLearning #DeepLearning #100DaysofMLCode

4

45

172

Lavanya 🐝

@lavanyaai

5 years

I get a ton of messages from people asking what the best way to learn Machine Learning is. Get @aureliengeron 's book. Read it. Play with the notebooks till you can recreate all dat code. Carry it around. Become best friends with it. 💑 #MachineLearning

8

19

165

Lavanya 🐝

@lavanyaai

4 years

In today's episode @l2k interviews @chipro about the gnarliest challenges in moving machine learning pipelines from research into production. Chip draws on lessons from her ML research at Snorkel, NVIDIA, Netflix & Primer. #machinelearning #deeplearning

1

39

163

Lavanya 🐝

@lavanyaai

4 years

If you're using #fastai , you can now track your model performance & hyperparams with @weights_biases . Great for – ✔️debugging models ✔️comparing performance ✔️hyperparameter optimization with 1 line of code #machinelearning #deeplearning #100daysofmlcode

Visualize, Track, and Compare fastai Models With Weights & Biases

In this article, we take a look at how to visualize, compare, and iterate on fastai models with Weights & Biases. Made by Boris Dayma using W&B

wandb.ai

3

39

160

Lavanya 🐝

@lavanyaai

4 years

GitHub Actions provide a way to incorporate software best practices into the world of #machinelearning . . @HamelHusain is showing you how to use em to automate your ML workflow. PS: yes there's an action to automate model tracking with W&B🤗 Watch here–

5

23

149

Lavanya 🐝

@lavanyaai

4 years

“Hands down one of the best AI & ML podcast episodes I’ve watched recently.” “Love who you bring on to these interviews. Very insightful questions.” “This channel is impressive as whole team & guests.” Thanks for all the love! 😇 Checkout more episodes:

1

24

147

Lavanya 🐝

@lavanyaai

3 years

Hi folks! If you watch ML podcasts or engage in ML communities avidly, I'd love to get your feedback. Reply to this tweet if you're down for a 20min call! 🙂 As a token of our gratitude, we’ll offer you a W&B shirt/Starbucks giftcard. #machinelearning #deeplearning #datascience

45

28

146

Lavanya 🐝

@lavanyaai

6 years

💯 advice from dad: "Imagine you've been validated, in every way you want to be validated - by your peers, heroes, society. What do you work on now? What's the one thing you're drawn to even after you've received complete societal validation? Start working on that thing now!"

1

24

141

Lavanya 🐝

@lavanyaai

3 years

1

11

142

Lavanya 🐝

@lavanyaai

3 years

We're thrilled to announce the new YOLOv5 x W&B integration! You can now visualize your datasets, log training progress in real-time, resume crashed runs across any device, & make your model training more robust! Find out more: #deeplearning

no-access

Weights & Biases, developer tools for machine learning

wandb.ai

2

32

139

Lavanya 🐝

@lavanyaai

4 years

Congrats @jeremyphoward & team on releasing Fastai v2! We're thrilled about the launch. Take Fastai for a spin: ◦ Visualize, track & compare Fastai models ◦ Semantic segmentation with Fastai #deeplearning #machinelearning

Weights & Biases with fastai

Colaboratory notebook

colab.research.google.com

1

33

135

Lavanya 🐝

@lavanyaai

4 years

Fascinating exploration of why deep ensembles work better than single deep neuralnets by @RisingSayak . Based on ideas presented in Deep Ensembles: A Loss Landscape Perspective by @stanislavfort & @balajiln . #machinelearning #deeplearning #100daysofmlcode

Understanding the Effectivity of Ensembles in Deep Learning

In this article, we dissect ensembles in order to provide different insights that are useful for understanding the dynamics of deep neural networks in general.

wandb.ai

1

38

124

Lavanya 🐝

@lavanyaai

5 years

Pretty deep into computer vision & I've never been moar excited in my life! 😍 Finding machine learning was like finding my work soulmate. It's exhilarating & peaceful & challenging & all-consuming in the best possible way & I wanna do it for the rest of my life! #100DaysOfMLCode

3

1

125

Lavanya 🐝

@lavanyaai

3 years

Can Apple's M1 help you train models faster & cheaper than NVidia's V100? In this post, our in-house investigative reporter extraordinaire @vanpelt analyzes runtimes, energy usage, & performance of a Tensorflow model on the two to find the answer. 🧐

Can Apple’s M1 Help You Train Models Faster & Cheaper Than NVIDIA’s V100?

In this article, we analyze the runtime, energy usage, and performance of Tensorflow training on an M1 Mac Mini and Nvidia V100. .

wandb.ai

3

25

121

Lavanya 🐝

@lavanyaai

5 years

Let's get more women on the stage! ❤️ I just built an app to find + book women in tech speakers. Ladies, would love for you to sign up! Conference organizers, we're adding more women to this list constantly! Book em! #WomeninTech #Women #Tech

14

54

117

Lavanya 🐝

@lavanyaai

4 years

See how a neural network learns to render new views from a learned neural representation of a single scene. We also visualize the effects of tweaking learning rates, embedding sizes etc 🛠️ #machinelearning #deeplearning #100daysofmlcode

NeRF – Representing Scenes as Neural Radiance Fields for View Synthesis

Publish your model insights with interactive plots for performance metrics, predictions, and hyperparameters. Made by Lavanya Shukla using Weights & Biases

wandb.ai

3

28

118

Lavanya 🐝

@lavanyaai

5 years

Doing big girl machine learning on my big girl curved monitor 😍

10

0

118

Lavanya 🐝

@lavanyaai

4 years

This was such a delight to read! 😍 Cannot recommend enough if you're curious about interpretability in neural networks! It even comes with tools that let you look under the hood of the models.

1

20

119

Lavanya 🐝

@lavanyaai

4 years

Today on Gradient Dissent: @josh_tobin_ joins @l2k to talk about his work with @OpenAI 's robotics team translating models from physics simulators to the real world, writing good unit tests for ML, & his incredible @full_stack_dl classes. #machinelearning

Josh Tobin — Productionizing ML Models

Josh Tobin, a former researcher at OpenAI and creator of Full Stack Deep Learning talks about professionalizing ML workflows for the real world, his work with the Robotics team and FSDL.

wandb.ai

1

33

109

Lavanya 🐝

@lavanyaai

3 years

Spreading the word about good experiment tracking hygiene in @chipro 's Stanford CS 329S class today. My favorite part is always the 🤯 moment when people see the move from log files/google docs to W&B. Track your models, kids.

2

12

111

Lavanya 🐝

@lavanyaai

5 years

. @weights_biases is officially included in Stanford's CS 197 class! 🚀 I wrote a quick tutorial on how to train a neural network using #PyTorch & track your experiments in W&B! Class: Code: #MachineLearning #100DaysofMLCode

PyTorch CNN MNIST

Colaboratory notebook

colab.research.google.com

1

25

107

Lavanya 🐝

@lavanyaai

3 years

In 2020, I trained 3,403 models over 450 hours, with 11 hours of GPU training time. I tuned 4 hyperparameters per model on average. Get insights on your model training with @weights_biases ! #myyearwrapped

2

1

107

Lavanya 🐝

@lavanyaai

2 years

. @l2k is interviewing Jensen, CEO of @nvidia , next week on our podcast, Gradient Dissent. What questions would you guys like him to ask Jensen about NVIDIA, GPUs, what he's cooking up next? Reply in this thread! 🙂 #deeplearning #machinelearning

15

14

107

Lavanya 🐝

@lavanyaai

4 years

What happens when you train only the BatchNorm layers of a network, with all other weights frozen to random initializations? Turns out you get a network with surprisingly high performance. ✍️🏼 @RisingSayak #machinelearning #deeplearning #100daysofmlcode

0

29

105

Lavanya 🐝

@lavanyaai

4 years

Recommend this 🔑 article on being a 10x data scientist. Includes 💯 nuggets like: "The only way to build trust with the scientific community is to commit to radical transparency ... post all your training runs to a public dashboard via @weights_biases ."

1

21

100

Lavanya 🐝

@lavanyaai

5 years

I got the "but you don't look like a programmer" from an 8 yr old girl today and it broke my heart that we're teaching arbitrary gender stereotypes to kids that young. 💔 I can't wait to have a daughter someday and raise her to be a proud badass nerd and embrace her femininity!

6

11

99

Lavanya 🐝

@lavanyaai

4 years

What happens when a transformer meets a twitter account? Find out for yourself! 🤔 In 5 minutes, fine-tune a pre-trained transformer on anyone's tweets, just by clicking a couple of buttons. 🛸 Try it here #machinelearning #deeplearning #100daysofmlcode

Hugging Tweets: Train a Model to Generate Tweets

In this article, we demonstrate how to fine-tune a pre-trained HuggingFace Transformer on anyone's Tweets in five minutes. Made by Boris Dayma using W&B

wandb.ai

1

20

97

Lavanya 🐝

@lavanyaai

5 years

Found this while doing research for another project! State of the art models/papers (with code!) for ImageNet, in one place! Excellent starting point if you wanna use transfer learning for your image classification project! #MachineLearning #DataScience

1

19

94

Lavanya 🐝

@lavanyaai

4 years

Your new favorite ML podcast is ◦ Coming Soon ◦

4

90

Lavanya 🐝

@lavanyaai

1 year

We're excited to bring you our first ever meetup in London on April 20th! Join our CEO @l2k and @EMostaque , CEO of @StabilityAI for a night of talks on LLMs, Q&As, drinks and hanging with like-minded ML engineers! 👩‍💻 We have limited seats, register here:

6

16

92

Lavanya 🐝

@lavanyaai

8 years

@balajis As someone who loves India & @pmarca equally, this perspective might help! | Peace Between All Rationalists

2

69

36

Lavanya 🐝

@lavanyaai

2 years

So excited to announce our new @OpenAI integration! You can now add one line of code to fine-tune your GPT-3 model with OpenAI's API and sync all training metrics, datasets and models to your W&B dashboard. Try it! 💻 openai wandb sync

0

15

88

Lavanya 🐝

@lavanyaai

4 years

Reading this post from @dalmiaman where gives a play by play of how he won a #Kaggle silver medal. 🏅 Fascinating read through his initial struggles, journey to finding the final solution & everything he learned in between. #deeplearning #machinelearning

1

18

85

Lavanya 🐝

@lavanyaai

4 years

Did you know you can massively accelerate model training time w/ a Keras utility wrapper function? My wonderful colleague Stacey shows you the magic trick of data-parallel distributed training in this post! #machinelearning #deeplearning #100daysofmlcode

0

19

83

Lavanya 🐝

@lavanyaai

4 years

If you're doing ML & need a community of people to nerd out with – W&B Forum is it. We have folks entering & winning hackathons together, getting help on weekend projects, talking shop. It's a great time🥰 #MachineLearning #DeepLearning #100DaysofMLCode

1

10

83

Lavanya 🐝

@lavanyaai

4 years

I made a couple resources to get you started with Weights & Biases: + Visualize model predictions (images, videos, audio, point clouds) + Track model performance Lemme know what you think🤗 #Kaggle #DeepLearning #MachineLearning

5

19

84

Lavanya 🐝

@lavanyaai

1 year

500 people have registered for our London meetup with @l2k and @StabilityAI this month. So we've booked a larger, sicker venue. We still have a couple spots left. Register here: See you April 20th!

6

19

82

Lavanya 🐝

@lavanyaai

2 years

I’ll be in London Jan-March. Would love to meet with ML engineers based in the area. What are some local ML communities I should check out? Who should I meet?

9

4

83

Lavanya 🐝

@lavanyaai

4 years

We're doing a series of posts on machine learning in production. 👩‍🔬 First up – Distributing model training workloads across multiple GPUs by @RisingSayak (useful for large, real world datasets and models). #machinelearning #deeplearning #100daysofmlcode

Distributed Training in tf.Keras With Weights & Biases

This article explores the ways to distribute your training workloads with minimal code changes and analyze system metrics with Weights & Biases.

wandb.ai

0

25

84

Lavanya 🐝

@lavanyaai

5 years

Math is beautiful. One of the best things about machine learning is falling in love with Math again! ❤️

1

7

81

Lavanya 🐝

@lavanyaai

5 years

Searching through high dimensional hyperparameter spaces to find the best model gets unwieldy fast. 🙉 Excited to share this intro to running hyperparameter sweeps using @weights_biases in an organized way! #MachineLearning #DeepLearning #100DaysofMLCode

Intro to Hyperparameter Sweeps with W&B.ipynb

Colaboratory notebook

colab.research.google.com

1

24

80

Lavanya 🐝

@lavanyaai

8 years

This is exciting! | Wikipedia starts work on $2.5m internet search engine project to rival Google

0

62

20

Lavanya 🐝

@lavanyaai

1 year

I wrote a little article for @Forbes on how we grew @weights_biases to a unicorn. Part 1 is out now!

2

10

80

Lavanya 🐝

@lavanyaai

5 years

MNIST is the secret handshake we use to introduce people into the world of machine learning. 🤙🏼 In this @weights_biases dashboard, I dive deep into what a state of the art model (99.4% acc) gets wrong about MNIST! #MachineLearning #DataScience

lavanya

Weights & Biases, developer tools for machine learning

wandb.ai

1

20

79

Lavanya 🐝

@lavanyaai

4 years

The 2nd episode of Gradient Dissent is live! This week @l2k talks to @nkoumchatzky about how NVIDIA uses machine learning in production for self driving. This was a fascinating conversation. We really hope you enjoy it! #machinelearning #deeplearning

Nicolas Koumchatzky — Machine Learning in Production for Self-Driving...

👨🏻‍💻Today our guest is Nicolas Koumchatzky.Nicolas Koumchatzky is the Director of AI infrastructure at NVIDIA, where he's responsible for MagLev, the prod...

www.youtube.com

3

32

78

Lavanya 🐝

@lavanyaai

1 year

Celebrate the future of ML with us in San Francisco. We’re hosting a one-day user conference on how GenAI is transforming the world, and tickets are going fast! You’ll hear from the creators of the most exciting ML tools like @LangChainAI , @OpenAI ,

5

18

78

Lavanya 🐝

@lavanyaai

4 years

Does model size matter? 🤔 @jxmorris12 does an excellent job comparing @huggingface 's BERT and DistilBERT. #machinelearning #deeplearning #100daysofmlcode

jack-morris

Weights & Biases, developer tools for machine learning

wandb.ai

0

20

76

Lavanya 🐝

@lavanyaai

3 years

We’re excited to launch Fully Connected, v2 of our ML community today! FC brings together ML engineers to ⭐️share research ideas ⭐️learn from industry leaders ⭐️discover the latest tools & papers ⭐️collaborate on projects together Everyone is welcome🙂

2

14

79

Lavanya 🐝

@lavanyaai

4 years

What's a good weight initialization strategy for your deep learning model? In this post @RisingSayak does a great job breaking down the effects of weight initialization strategies on model performance! ⚖️ #machinelearning #deeplearning #100daysofmlcode

Effects of Weight Initialization on Neural Networks

This article explores why weight initialization matters, before providing a comparison of a range of weight initialization methods with Weights & Biases.

wandb.ai

0

20

76

Lavanya 🐝

@lavanyaai

5 years

I made a quick video to walk y'all through picking the optimal neural net architecture by tracking your metrics, using @weights_biases in your Kaggle kernels. 👩‍🎨 • Kernel: • Demo: #MachineLearning #DataScience

Kaggle <> Weights and Biases

null

www.loom.com

0

15

76

Lavanya 🐝

@lavanyaai

5 years

I was just accepted as a writer on @TDataScience and as a long time reader, I'm so thrilled to be writing for them! 😍

5

4

76

Lavanya 🐝

@lavanyaai

4 years

Remote work is hard. Remote machine learning is even harder. @l2k talks to leaders at different sized ML teams on how they track experiments, debug models, keep teams aligned, & manage distributed training. #machinelearning #deeplearning #100daysofmlcode

Machine Learning Experiment Tracking

Why is experiment tracking so important for doing real world machine learning?

towardsdatascience.com

1

26

72

Lavanya 🐝

@lavanyaai

4 years

Our guest this week is @HamelHusain , Staff Machine Learning Engineer at @Github . He joins @l2k to talk about Github Actions, CodeSearchNet challenge and the tools they're building to advance progress in AI! #machinelearning #deeplearning #100daysofmlcode

0

35

71

Lavanya 🐝

@lavanyaai

2 years

I am blown away by the speed at which the W&B team is reporting on the latest ML news – 3-4 pieces of what to pay attention to everyday! 🙂 If y'all haven't seen it, you need to –

1

11

70

Lavanya 🐝

@lavanyaai

3 years

This team built a deep learning sea ice forecasting system, to help reduce risks from rapid sea ice loss and they used @weights_biases to train their models! Saving polar bears and helping the global climate – def one of my fav applications of W&B! 😍

Seasonal Arctic sea ice forecasting with probabilistic deep learning

Nature Communications - Accurate seasonal forecasts of sea ice are highly valuable, particularly in the context of sea ice loss due to global warming. A new machine learning tool for sea ice...

www.nature.com

1

12

70

Lavanya 🐝

@lavanyaai

5 years

Highly recommend this video/paper on • adversarial attacks on neural nets • how changing just *one* pixel lets us fool almost any neural net • most datasets contain features that are predictive, but can be flipped by adversarial attacks (contd…) #MachineLearning #DataScience

2

22

68

Lavanya 🐝

@lavanyaai

4 years

Reproducing papers alone is a major undertaking – join the slack channel to get guidance, work on paper reproductions together, & get your questions answered. 👩‍💻 Community: , ml-reproducibility channel 👨‍💻 Learn more: #deeplearning

Call for reproducing papers (Outdated) | Notion

Supporting the Reproducibility Challenge participants

wandbai.notion.site

3

8

70

Lavanya 🐝

@lavanyaai

4 years

PyTorch Lightning lets you decouple your science code from engineering code. Ayush shows you how to visualize Lightning models and optimize model hyperparameters with an easy W&B integration. #machinelearning #deeplearning #100daysofmlcode

Weights & Biases

Weights & Biases, developer tools for machine learning

wandb.ai

0

17

67

Lavanya 🐝

@lavanyaai

3 years

If you are excited about building the next generation of ML tools and joining the W&B 🚀, we're hiring on the growth, eng, product, sales, & data science teams!

Weights & Biases

Job openings at Weights & Biases

jobs.lever.co

4

14

66

Lavanya 🐝

@lavanyaai

2 years

Super excited to announce a new investment in Weights & Biases by NVIDIA! To celebrate, check out this fabulous interview @l2k did with NVIDIA CEO, Jensen:

Jensen Huang — NVIDIA's CEO on the Next Generation of AI and MLOps

Jensen Huang is founder and CEO of NVIDIA, whose GPUs sit at the heart of the majority of machine learning models today.Jensen shares the story behind NVIDIA...

www.youtube.com

Weights & Biases

@weights_biases

2 years

Today, we’re proud to announce an investment from the team at @nvidia . This means a lot to us here at W&B as we continue to build out the best platform for ML developers. You can read all about our growing partnership here:

5

18

154

3

6

65

Lavanya 🐝

@lavanyaai

4 years

In this episode of Gradient Dissent, @zacharylipton talks to @l2k about his fascinating journey from musician to Professor, applications of ML in medicine, counterfacutally augmented data and algorithmic fairness. It's a great listen! #machinelearning

0

19

65

Lavanya 🐝

@lavanyaai

4 years

Can supervised contrastive learning really outperform cross-entropy? In this report, @RisingSayak and Shweta introduce SCL and present a plethora of experiments to validate its efficiency. #machinelearning #deeplearning #100daysofmlcode

Improving Image Classifiers With Supervised Contrastive Learning

This article introduces supervised contrastive learning, an adaption of contrastive learning in the field of fully supervised learning problems.

wandb.ai

0

21

63

Lavanya 🐝

@lavanyaai

4 years

We're excited to announce our newest tool, Artifacts. With Artifacts you can store & version your datasets, models & results. 👨‍💻 Read the behind-the-scenes story of how Artifacts came to life by @shawnup . #machinelearning #deeplearning #100daysofmlcode

3

26

62

Lavanya 🐝

@lavanyaai

4 years

Our feature reports today focus on NLP 101! We take you under the hood of RNNs and LSTMs by implementing them in NumPy from scratch! It's quite a ride. RNNs: LSTMs: #deeplearning #machinelearning #100daysofmlcode #nlp

Under the Hood of Long Short Term Memory (LSTM)

This article explores how LSTM works, including how to train them with NumPy, vanish/explode the gradient, and visualize their connectivity. .

wandb.ai

0

16

63

Lavanya 🐝

@lavanyaai

5 years

Haven't had time to Kaggle seriously the last few months, so this was a sweet surprise - 205 out of 100,181! Getting closer to #Kaggle Master! 💃🏼

2

61

Lavanya 🐝

@lavanyaai

5 years

It’s game time! Never built a computer from scratch before, but now seems as good a time as any to start! 😌 #MachineLearning #DataScience

7

2

62

Lavanya 🐝

@lavanyaai

3 years

Come hang with us tomorrow and learn about making your ML workflows reproducible 🙂

abhishek

@abhi1thakur

3 years

Lavanya🦋, Head of Growth at Weights & Biases will be talking about "Reproducible machine learning at scale" on my YouTube channel this Friday at 6PM CET / 9.30 PM IST / 9 AM PDT. Check out the event here: and click on the🔔icon to get reminded!

0

4

37

2

10

64

Lavanya 🐝

@lavanyaai

3 months

I'm writing a series posts showing anyone how to build & productionize an LLM powered app. Here's the first one where I go from 17% to 91% accuracy through Prompt Engineering on a real world use case! 👩🏼‍💻 Notebook: ✍🏼 Blog post:

Going from 17% to 91% Accuracy through Prompt Engineering on a Real-World Use Case

This is the first in a series all about real world LLM-app building. Today, we're going to build a customer success ticket classifier and improve its accuracy five fold.

wandb.ai

1

13

63

Lavanya 🐝

@lavanyaai

4 years

We're doing an AMA on @huggingface in our slack community – Bring all your questions on picking & fine tuning HuggingFace models, & anything else you want to talk about! This Thursday – 9am PST / 12pm EST #machinelearning #deeplearning #100daysofmlcode

0

16

62

Lavanya 🐝

@lavanyaai

4 years

#ComputerVision twitter – I'm very excited to dive deeper into explainability of vision models this long weekend. If you have any papers you think I should read, please send them my way! Thank you 🙂

11

6

61

Lavanya 🐝

@lavanyaai

4 years

Check out @kevinkwshen 's amazing #kaggle kernel, where he shows you how to visualize a FasterRCNN's predictions and find the best set of hyperparameters. In v2, he'll dig deeper into FasterRCNN's hyperparameters.

Hyperparameter Search for FasterRCNN

Explore and run machine learning code with Kaggle Notebooks | Using data from Global Wheat Detection

www.kaggle.com

0

12

62