使用Player FM应用程序离线!
Vector Quantization for NN Compression with Julieta Martinez - #498
Manage episode 296743934 series 2355587
Today we’re joined by Julieta Martinez, a senior research scientist at recently announced startup Waabi.
Julieta was a keynote speaker at the recent LatinX in AI workshop at CVPR, and our conversation focuses on her talk “What do Large-Scale Visual Search and Neural Network Compression have in Common,” which shows that multiple ideas from large-scale visual search can be used to achieve state-of-the-art neural network compression. We explore the commonality between large databases and dealing with high dimensional, many-parameter neural networks, the advantages of using product quantization, and how that plays out when using it to compress a neural network.
We also dig into another paper Julieta presented at the conference, Deep Multi-Task Learning for Joint Localization, Perception, and Prediction, which details an architecture that is able to reuse computation between the three tasks, and is thus able to correct localization errors efficiently.
The complete show notes for this episode can be found at twimlai.com/go/498.
699集单集
Vector Quantization for NN Compression with Julieta Martinez - #498
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Manage episode 296743934 series 2355587
Today we’re joined by Julieta Martinez, a senior research scientist at recently announced startup Waabi.
Julieta was a keynote speaker at the recent LatinX in AI workshop at CVPR, and our conversation focuses on her talk “What do Large-Scale Visual Search and Neural Network Compression have in Common,” which shows that multiple ideas from large-scale visual search can be used to achieve state-of-the-art neural network compression. We explore the commonality between large databases and dealing with high dimensional, many-parameter neural networks, the advantages of using product quantization, and how that plays out when using it to compress a neural network.
We also dig into another paper Julieta presented at the conference, Deep Multi-Task Learning for Joint Localization, Perception, and Prediction, which details an architecture that is able to reuse computation between the three tasks, and is thus able to correct localization errors efficiently.
The complete show notes for this episode can be found at twimlai.com/go/498.
699集单集
所有剧集
×欢迎使用Player FM
Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。