Foundational challenges in assuring alignment and safety of large language models
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …
language models (LLMs). These challenges are organized into three different categories …
Transfer learning for radio frequency machine learning: a taxonomy and survey
Transfer learning is a pervasive technology in computer vision and natural language
processing fields, yielding exponential performance improvements by leveraging prior …
processing fields, yielding exponential performance improvements by leveraging prior …
Toward transparent ai: A survey on interpreting the inner structures of deep neural networks
The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …
Similarity of neural network representations revisited
Recent work has sought to understand the behavior of neural networks by comparing
representations between layers and between different trained models. We examine methods …
representations between layers and between different trained models. We examine methods …
Emerging cross-lingual structure in pretrained language models
We study the problem of multilingual masked language modeling, ie the training of a single
model on concatenated text from multiple languages, and present a detailed study of several …
model on concatenated text from multiple languages, and present a detailed study of several …
Individual differences among deep neural network models
Deep neural networks (DNNs) excel at visual recognition tasks and are increasingly used as
a modeling framework for neural computations in the primate brain. Just like individual …
a modeling framework for neural computations in the primate brain. Just like individual …
Grounding representation similarity through statistical testing
To understand neural network behavior, recent works quantitatively compare different
networks' learned representations using canonical correlation analysis (CCA), centered …
networks' learned representations using canonical correlation analysis (CCA), centered …
Joint a-snn: Joint training of artificial and spiking neural networks via self-distillation and weight factorization
Emerged as a biology-inspired method, Spiking Neural Networks (SNNs) mimic the spiking
nature of brain neurons and have received lots of research attention. SNNs deal with binary …
nature of brain neurons and have received lots of research attention. SNNs deal with binary …
Similarity and matching of neural network representations
A Csiszárik, P Kőrösi-Szabó… - Advances in …, 2021 - proceedings.neurips.cc
We employ a toolset---dubbed Dr. Frankenstein---to analyse the similarity of representations
in deep neural networks. With this toolset we aim to match the activations on given layers of …
in deep neural networks. With this toolset we aim to match the activations on given layers of …
Similarity of neural network models: A survey of functional and representational measures
Measuring similarity of neural networks to understand and improve their behavior has
become an issue of great importance and research interest. In this survey, we provide a …
become an issue of great importance and research interest. In this survey, we provide a …