Sentim (@SentimOfficial) header
Sentim (@SentimOfficial) profile picture

Helping people and machines better understand emotions with a focus on machine learning and neural networks.

Joined December 2017
Photo by Sentim (@SentimOfficial)
Visualizing Weights — A new Distill article by @csvoss, @nickcammarata, @gabeeegoooh, @mpetrov, @ludwigschubert, Ben Egan, Swee Kiat Lim, and @ch402. This is the seventh article in the circuits thread. distill.pub/2020/circuits/vi…
41
3
172
High-Low Frequency Detectors — A new Distill article by @ludwigschubert, @csvoss, and @ch402. This is the fifth article in the circuits thread. distill.pub/2020/circuits/fr…
1
27
2
106
Great explanations for how different interpretation methods work on a high level.
Sentim retweeted
We’ve developed two neural networks which have learned by associating text and images. CLIP maps images into categories described in text, and DALL-E creates new images, like this, from text. A step toward systems with deeper understanding of the world. openai.com/multimodal/
90
899
328
2,872
I'm happy to announce that our MuZero paper has been published in Nature: go.nature.com/38qb2I8 ! Please see our official blog post https://xitter.cf/t.co/buMXAhMarh for more; also see my personal blog for a high level description of MuZero: furidamu.org/blog/2020/12/22…
24
314
35
1,509
Language models like GPT-2 memorize text from their training data. This blog discuss the legal and privacy implications. Are models: * subject to GDPR's "right to be forgotten" law? * infringing on copyright? * illegally misusing data? bair.berkeley.edu/blog/2020/…
6
94
13
423
New video on #machinelearning! What is pooling, why do we use it, and how does it relate to convolutional neural networks? youtu.be/KKmCnwGzSv8 #datascience #artificialintelligence #neuralnetworks
Interpretability of AI systems is crucial for their adoption, but how can it be achieved, and where is the research at? Read our new overview by Owen Shen on that: thegradient.pub/interpretabi…
2
33
3
159
Adapting to your data distribution changing after you train your model remains one of the big challenges of Machine Learning. Check out our latest blog post on work addressing this challenge - ai.stanford.edu/blog/adaptiv…
2
71
4
311
A system capable of answering any factual questions can enable many useful applications. My new post delves into how we can build an open-domain question answering model, with neural networks or with access to a powerful pre-trained language model. lilianweng.github.io/lil-log…
4
40
3
238
Convolutional neural networks can be confusing. Learn how they work in four and a half minutes. #machinelearning #intuitiveml #artificialintelligence #datascience #deeplearning youtube.com/watch?v=UzfRnZqP…
New blog post! Fine-tuning ResNet-18 for Audio Classification: Reproducible experiments using fastai, fastaudio, and wandb sweeps to explore hyperparameters for achieving high accuracy on the ESC-50 dataset. wandb.ai/jhartquist/fastaudi… Special thanks to @fastdotai @wandb
7
26
A video answering the questions: What is bagging in machine learning? How does it work? Why do we care? youtu.be/w2r_PCNeCWI #machinelearning #intuitiveml #artificialintelligence
Ensembles can be very useful tools to improve machine learning performance! Watch youtube.com/watch?v=VV7UxYSj… to learn more! #MachineLearning #ArtificialIntelligence #DeepLearning
1
Transformer’s attention mechanism can be linked to other cool ideas in AI - Indirect Encoding in Neuroevolution attentionagent.github.io - Hopfield Networks with continuous states arxiv.org/abs/2008.02217 - Graph Neural Networks with multi-head attention thegradient.pub/transformers…
6
78
3
385