Audio data: ResNet/EffNet That's right -- image models for audio data. My favorite way of starting audio problems is converting the audio to a spectrogram and throwing an image model at it. Give it a shot!

If you want to learn more about: • Transformers and ViT • GPT-3 and CLIP Pi School is hosting free tech talks. ↑ Make sure you follow them. Don't miss this chance! (Their AI program started 2 weeks ago. We will be following along with a few practical problems!)

AI is a form of empirical philosophy. I bet that if Plato, Phyrro, Descartes or Wittgenstein were around now, they’d be tinkering with neural networks. With language models, with generative models and with agents.

Building out an ML project will teach you more about applied ML than any textbook.

🔥Preprint out: `Toward a realistic model of speech processing in the brain with self-supervised learning’: arxiv.org/abs/2206.01685 by J. Millet*, Charlotte Caucheteux @ICML24* and our wonderful team: The 3 main results summarized below 👇

800 free #ComputerScience classes you can take online right now, with video lectures: bit.ly/3472Iia ———— #BigData #DataScience #AI #ArtificialIntelligence #MachineLearning #DeepLearning #ComputerVision #Robotics #QuantumComputing

I'll be joining SFU as an Assistant Prof and NVIDIA as a Research Scientist! Currently looking for MSc/PhD students. If you are interested in working together on topics in RL, animation, and legged robots, apply through Simon Fraser University.

Specially when Colab kernel resets before saving the model 😅 #ai #ml #DeepLearning

Right one more time. Happy to announce the release of #StableDiffusion for researchers. Public release soon. GitHub here: github.com/CompVis/stable… Blogpost (correct link) here: stability.ai/blog/stable-di… More on Stability AI later when I figure out how to use the internet 🫣

Using a library without reading the documentation

It's been devastating to see the effects of torrential rains in Pakistan, with one-third of the country under water and more than 33 million people affected. If you can, please consider donating at pakistan.unicef.org.au/cricket UNICEF Australia | Usman Khawaja

Python 3.11 is out! 🎉 This is one of the most exciting releases in a while, including significant speed upgrades and better error messages. Here's what's new:

Karlo - large scale replication of unCLIP, the DALL-E 2 technique is now on Hugging Face try out the Gradio Demo: huggingface.co/spaces/kakaobr…

95% of ML tutorials: • Curated dataset • Basic features • Random 20% k-fold • Hyperparams that just work Real life: • Messy/nonexistent dataset • Weeks of feature engineering • Complex cross-validation setup • Thoroughly tuned hyperparams We need to bridge this gap.

I hope Sundar calls theirs ChaatGPT.

The true story of SAAS founders

dear people! always, always trust your first gut instincts. If you genuinely feel in your heart and soul that something is wrong, it usually it.