ResNet, every mention
15 scenes across 7 shows · ← back to ResNet
tap a year for its mentions
Latent Space 10
the a16z Podcast 4
No Priors 1
All-In 1
Big Technology 1
Cheeky Pint 1
the MAD Podcast 1
every year every show Latent Space 10 the a16z Podcast 4 Cheeky Pint 1 No Priors 1 the MAD Podcast 1 Big Technology 1 All-In 1
Verbatim, from the transcripts: passages where ResNet comes up on Latent Space, the a16z Podcast, Cheeky Pint, No Priors, the MAD Podcast
How Open Source Became AI's Backbone | Inferact with a16z
Cooking with OpenAI’s Research Chief: AGI, o1, Evals, and Scaling Laws — Mark Chen
Inside xAI: Building Grok Imagine in 3 Months, Videogen vs World Models, and Video Agents— Ethan He
AI is Already Building AI — Google DeepMind’s Mostafa Dehghani
- ▶ 40:46 Mostafa Dehghani Uh, four hundred billion parameter language models, but the biggest model that we have on the vision side is just like maybe a hundred million, like a rest that, like what, why, like, like why there's no benefit of a scale.
Reiner Pope of MatX on accelerating AI with transformer-optimized chips
- ▶ 2:50 Reiner Pope LSTMs, uh, and, and Confidence and ResNet and Inception.
🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
- ▶ 8:26 Varun Mohan If it's a vision, they should be fine tuning resonant or using something like clip, like the less work they can do the better.
Why Can't AI Make Its Own Discoveries? — With Yann LeCun
- ▶ 57:25 Yann LeCun It's, uh, the paper is called, uh, ResNet.
Best of 2024 in Vision [LS Live @ NeurIPS]
- ▶ 41:33 Peter Robicheaux Uh, yeah, one thing I want to add is just, like, or just to summarize, basically, is that, like, until, you know, we haven't really seen a combination of transformer-based, uh, object detectors and, uh, fancy losses, and Polygema suffers…
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
Breaking down the OG GPT Paper by Alec Radford
- ▶ 18:39 unnamed speaker So, for example, you can use ResNet that was trained to classify ImageNet. 3 times in the scene
E167: Google's Woke AI disaster, Nvidia smashes earnings (again), Groq's LPU breakthrough & more
- ▶ 35:31 Chamath Palihapitiya That didn't work out.
The End of Finetuning — with Jeremy Howard of Fast.ai
- ▶ 1:19:13 Jeremy Howard Like, I want to see, there was a great, um, paper about, uh, Resnets, uh, a few years ago, um, that showed how, that was able to, like, plot a kind of projected three-dimensional loss surface for a ConvNet, um, with and without, um, skip…
RWKV: Reinventing RNNs for the Transformer Era
- ▶ 1:08:56 Eugene Cheah Is that ever since that initial paper came out, there was ResNet, there's, um, I think there's two more, there's a few more additional papers coming out, one from Microsoft, one, uh, one from other organizations that are literally…
No Priors Ep. 13 | With Jensen Huang, Founder & CEO of NVIDIA
- ▶ 15:52 Jensen Huang And so CNNs, to Resnets, to RNNs, to LSTMs, to, you know, all kinds of new models and, and scaling them larger and larger, making great strides in perception models, particularly.
Explaining AI
- ▶ 0:43 Harry Shum Ah, some of you might know that, you know, ResNet now is the most popular deep neural net, ah, in computer vision.