Sentim retweeted
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…
Sentim retweeted
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…
Great explanations for how different interpretation methods work on a high level.
How have interpretation methods for image recognition developed over the past few years? In our latest piece, @si3luwa provides a fascinating visual history: thegradient.pub/a-visual-his…
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/
Sentim retweeted
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…
Sentim retweeted
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/…
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
Sentim retweeted
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…
This was totally worth reading on my computer instead of my phone like I normally browse twitter.
Understanding RL Vision -- A new Distill article by @JacobHHilton, @nickcammarata, @shancarter, @gabeeegoooh, and @ch402.
distill.pub/2020/understandi…
Sentim retweeted
Google's `Hum to Search`
ai.googleblog.com/2020/11/th…
What is a convolutional neural network's receptive field? #cnn #intuitiveml #machinelearning #deeplearning #datascience
youtu.be/70A3uYfM1qA
Sentim retweeted
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…
Sentim retweeted
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…
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…
Boost model performance with boosting! #intuitiveml #deeplearning #machinelearning #datascience
youtube.com/watch?v=hZObUx6A…
Sentim retweeted
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
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
Sentim retweeted
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…















