Machine learning engineer @benevolent_ai. I love collaborating, learning, and problem-solving.
New Jersey, USA
Joined November 2018
- Tweets91
- Following447
- Followers90
- Likes400
David Aponte retweeted
Thanks @mlopscommunity for this really great animation based on our Eng Blog article by Shaji Chennan Kunnummel and Iaroslav Tymchenko. #machinelearning #engineering
youtu.be/Vfgr8V-EOEA
Checkout a new book by one of the MLOps Community members!
8 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn #MachineLearning by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
manning.com/books/machine-le…
David Aponte retweeted
Excited to announce the launch of GPT-42.
- Half the size of GPT-3 (100 billion parameters)
- runs on 775 watts a day (2000 calories)
- can do one-shot learning
- multi-modal
- does NOT require 9,000 GPUs
- 300,000 years worth of evolution research!
Inference API coming soon!
“It always takes longer than you expect, even when you take into account Hofstadter’s Law” - Hofstadter’s Law
Working on a repo where you can build pipelines and productionize them using AWS and GCP. Use it to start your own project! #MachineLearning #DataScience #softwareengineering github.com/aponte411/model_p…
David Aponte retweeted
A while ago, I thought doing things in a clever way was cool. Now, I understand that simple is better than clever. Clever is mostly showing off.
David Aponte retweeted
So, "deep learning" is the idea of doing representation learning via a chain of learned feature extractors. It's all about describing some input data via *deep hierarchies of features*, where features are *learned*.
A further question is then: is the brain "deep learning"?
David Aponte retweeted
Looking back, my last decade was like a neural network. Some parts were linear. Some were nonlinear. I never seemed to get enough data, and always got stuck in local minima. There was a lot of learning. I can't explain how any of it worked, but the results came out alright.
David Aponte retweeted
ADN #PyConLatam! 💙
🇲🇽 🐍
🇧🇴🐍
🐍
🐍 🇦🇷
🐍 🇨🇱
🐍 🇧🇷
🐍 🇭🇹
🐍 🇭🇳
🐍 🇨🇴
🇵🇦
🇨🇺 🐍
🇩🇴 🐍
🇳🇮 🐍
🇻🇪 🐍
🇦🇷 🐍
🇸🇻 🐍
🐍
🐍 🇵🇪
🐍 🇨🇷
🐍 🇬🇹
🐍 🇵🇾
🐍 🇨🇱
🐍 🇺🇾
🇵🇾
🇪🇨 🐍
David Aponte retweeted
🌊 = 🚰()
🟫 = 🚜()
with tf.GardenTape() as 📼:
x = 👨🌾(🟫, 🌊)
x = 🌅(x)
x = 👩🌾(x)
[🌷, 🌼, 🌻] = 📼.garden(x, [🌊, 🟫])
David Aponte retweeted
The scikit-learn TransformedTargetRegressor can make a fantastic addition to your workflow. Instead of transforming your target before fitting and then after prediction, it automates the process for you.
Here's an example from the Kaggle Housing competition
David Aponte retweeted
Colab now has a Data Table extension that allows interactive exploration of pandas dataframes with filtering and sorting. Details in colab.research.google.com/no…
David Aponte retweeted
If your classifier is "99% accurate", either you're using the wrong metric (a metric this high is not informative), or you have an overfitting or leakage problem.
Metrics are feedback points on the way towards better models. Not trophies to show off. They should be actionable.
David Aponte retweeted
Announcing our first international office in Medellin, Colombia! Landing AI, deeplearning.ai and AI Fund have teams there. AI needs to expand beyond a small handful of hubs like Silicon Valley and Beijing, and I’m bullish about Latin America. medium.com/@andrewng/ai-in-l…
David Aponte retweeted
"Study hard what interests you the most in the most undisciplined, irreverent, and original manner possible” - Richard Feynman
David Aponte retweeted
When I first got into data science, I had impostor syndrome, and I dealt with insecurity by not engaging with people, or acting like I knew everything. This was a mistake. The best way through it is to humbly engage with people - I've learned a lot more this way!
David Aponte retweeted
Amazing!! Deep Learning-based NLP techniques are going to revolutionize the way we write software. Here's Deep TabNine, a GPT-2 model trained on around 2 million files from GitHub. Details at tabnine.com/blog/deep #nlproc
