Lecture

Model Compression Techniques: Enhancing Neural Networks

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Related lectures (64)

Model Compression: Techniques for Efficient NLP Models

Explores model compression techniques in NLP, discussing pruning, quantization, weight factorization, knowledge distillation, and attention mechanisms.

Image compression

Explores image compression through various approaches like pixel and block level compression, Discrete Cosine Transform, quantization, and entropy coding.

Neural Signal Compression

Explores analog-to-digital conversion, neural signal optimization, multichannel architectures, and on-chip compression techniques in neuroengineering.

Provable Benefits of Overparameterization in Model Compression

Explores the provable benefits of overparameterization in model compression, emphasizing the efficiency of deep neural networks and the importance of retraining for improved performance.

Second-Order Model Compression

Explores second-order model compression for massive deep neural networks, showcasing compression techniques and their impact on model accuracy.

Optical Computing: All-Analog Photoelectronic Chip for Vision Tasks

Presents an all-analog photoelectronic chip for high-speed vision tasks, addressing challenges in classical computation and proposing a hybrid optical-electrical framework.

JPEG 2000: Image Compression

Explores image compression principles, focusing on JPEG 2000, covering transform-based coding, quantization, entropy coding, region of interest, error resilience, and software implementations.

Compressive Sensing

Explores compressive sensing theory and hardware implementations for signal reconstruction.

MP3 Compression

Explores MP3 encoding, emphasizing reducing bits through lossy compression and utilizing psycho-acoustic models for efficient filtering and quantization.

Applications of GAMP

Delves into applying the GAMP algorithm to simplify the lasso problem and analyze optimization challenges in neural networks.

Compressive Sensing of Neural Signals

Explores compressive sensing for neural signals, focusing on data reduction and efficient signal reconstruction.

Dimensionality Reduction: PCA and Autoencoders

Introduces artificial neural networks, CNNs, and dimensionality reduction using PCA and autoencoders.

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

JPEG XS & JPEG XL: Next-Gen Image Compression

Explores the cutting-edge JPEG XS and JPEG XL image compression standards, emphasizing their efficiency and versatility in various applications.

Compression: Prefix-Free Codes

Explains prefix-free codes for efficient data compression and the significance of uniquely decodable codes.

Image Processing II: Coding and Compression

Explores image coding, compression techniques, and wavelet-based methods for efficient data representation.

Information in Networked Systems: Functional Representation and Data Compression

Explores traditional information theory, data compression, data transmission, and functional representation lemmas in networked systems.

Data Compression and Entropy: Compression

Explores lossless data compression techniques, emphasizing efficient message representation and encoding strategies.

Sequence to Sequence Models: Overview and Applications

Covers sequence to sequence models, their architecture, applications, and the role of attention mechanisms in improving performance.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.