Machine Learning
1297 Threads
I have been thinking about @cHHillee's article about the state of ML frameworks in @gradientpub for almost a year now, as I've transitioned out of research to industry. It is a gre...
One of the best steps I’ve taken as a Software Engineer has been to get into Machine Learning. If you are looking for what's next in your career, here are some pointers to get you...
Beginning a thread on the ML engineer starter pack (please contribute): - ”example spark config” stackoverflow post - sklearn documentation - hatred for Airflow DAGs - awareness o...
100 day project.. First #ai #artificialintelligence #machinlearning #computerscience project #100dayproject.. 🌼 💪🌱 https://t.co/LQRG9NPE6I
Xelpmoc Design & Technology Ltd - Another Ycombinator in making? @XelpmocT is a Data Science Company and is essentially the reverse of the word "COMPLEX"as management believes in...
- NLP can help to inform NLP and vice versa - BERT has no sense of communicative intent - Language models don't really "understand" they are just good at predicting the next probab...
THREAD: Is it possible that Kubeflow pipeline is one of the best CI/CD tools for Kubernetes? I spent some time playing with Kubernetes & @kubeflow pipelines, and they have one fe...
This is absolutely amazing! 😍 Using @paperswithcode you can now keep track of progress as per the different building blocks of ML. For example, you can easily find out the progre...
Dear ML community, read past the abstract! Before you jadedly scream "why train a gajillion parameters on a gajillion TPUs," realize that @lepikhin et al. did so much more. Thread:...
The course of history now critically depends on whether GPT-4 and GPT-5 will show diminishing performance returns.
After reading the GPT-3 paper once, I highly recommended it. It contains interesting motivations about why the need for bigger models, particularly as it relates to the potential...
This is how I first learned about Neural Networks 😂 https://t.co/j5ZWCZsMmK
4/10 - Cut & paste your surroundings to Photoshop Code: https://t.co/cVddH3u3ik Book: @HOLOmagazine Garment: SS17 by @thekarentopacio Type: Sainte Colombe by @MinetYoann @Produc...
I 100% recommend this @karpathy talk about multi-task learning at scale. @ericjang11 covers some of the main points well. But as the 1st ML engineer at a startup that sells an ML...
Thread for beginners; How to learn machine learning.
New tutorial!? Today I'm sharing a deeply personal post on Detecting #COVID19 in X-ray images with #Keras and #TensorFlow 2.0: https://t.co/ebHezQ38Y3 ? #DeepLearning #Python #M...
When I went to NeurIPS a month back, I noticed a couple of interesting books that I wanted to share. Here are a few that caught my attention and that I would recommend if you are s...
What is your favorite mathematical trick in machine learning? #MachineLearningTrick Please add in comment(s) and RT! Thanks.
Machine learning for single cell biology: insights and challenges by Dana Pe’er. #NeurIPS2019 https://t.co/w8seVA09GQ
Bin Yu discussing three principles of data science and interpretable machine learning. #NeurIPS2019 https://t.co/jUINeU4jhw
Machine learning portfolio tips 1. Good ideas come from ML sources that are a bit quirky. - NeurIPS from 1987 - 1997 - Stanford’s CS224n & CS231n projects - Twitter likes from ML...
i bet this isn't the only plagiarizing paper on arxiv. @sirajraval is getting called out partially because he is an influencer, and we don't want fraudulent influencers in ML. as...
Just read an inspirational transfer learning NLP paper. The key is in how you want the model to perform transfer learning. You want the model to learn sequentially on tasks or you...
ResNet-50 on ImageNet now (allegedly) down to 224sec (3.7min) https://t.co/3Z77Edfj0u using 2176 V100s. Increasing batch size schedule, LARS, 5 epoch LR warmup, synch BN without mo...
