Vector Quantization for NN Compression with Julieta Martinez - #498

Показать описание

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.

Subscribe:

Apple Podcasts:
Spotify:
Google Podcasts:
RSS:
Full episodes playlist:
Subscribe to our Youtube Channel:

Podcast website:
Sign up for our newsletter:
Check out our blog:
Follow us on Twitter:
Follow us on Facebook:
Follow us on Instagram:

Рекомендации по теме

Комментарии

I wonder how much the PQ for DNN the way she described would add to the time complexity of training. But then again, VQ-VAE is already doing the clustering and quantization during training, without the feature permutation that is.

nauy

Vector Quantization for NN Compression with Julieta Martinez - #498

Neural Audio Compression | What is Residual Vector Quantization?

Vector Quantization for NN Compression with Julieta Martinez - #498

CNN Weight Compression Using Vector Quantization

CNN Weight Compressing using Vector Quantization

What is Learning Vector Quantization (LVQ) in Machine Learning?

tinyML Asia 2020 Kai YU: Structured Quantization for Neural Network Language Model Compression

Learning Vector Quantisers (LVQ) Explained by a student

Vector Quantization for Speech Processing #nlp #naturallanguageprocessing #machinelearning

Learning Vector Quantization in 60 Seconds | Machine Learning Algorithms

Learning Vector Quantization(LVQ) algorithm with solved example

Quantization vs Pruning vs Distillation: Optimizing NNs for Inference

Image Compression Using Optimized Vector Quantization Algorithm

191 Compressing an Image Using Vector Quantization

Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained...

Quantization in deep learning | Deep Learning Tutorial 49 (Tensorflow, Keras & Python)

Variable Rate Allocation for Vector-Quantized Autoencoders (ICASSP 2023)

Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

Learning Vector Quantization (LVQ) Neural Network - 2: Numerical Example

CNN Weight Compression Using Vector Quantization pdf Adobe Acrobat Reader DC 32 bit 2021 12 05 23

Vector Quantization and Learning Vector Quantization

Vector-Quantized Variational Autoencoders (VQ-VAEs) | Deep Learning

Hyperspherical Quantization: Toward Smaller and More Accurate Models

Model Compression Techniques for Deep Neural Networks | CS365

High Fidelity Neural Audio Compression | Paper & Code Explained