Memory-Based Model Editing at Scale

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.

In this thesis, we propose model order reduction techniques for high-dimensional PDEs that preserve structures of the original problems and develop a closure modeling framework leveraging the Mori-Zwanzig formalism and recurrent neural networks. Since high ...

Long-lasting memories are stored in a small set of neurons scattered throughout the brain, so-called engram cells. To define a stable engram each region of the brain involved in memory storage recruits between 5 and 20 percent of excitatory neurons. In par ...

Obesity and type 2 diabetes are associated with cognitive dysfunction. Because the hypothalamus is implicated in energy balance control and memory disorders, we hypothesized that specific neurons in this brain region are at the interface of metabolism and ...

We consider the problem of training a neural network to store a set of patterns with maximal noise robustness. A solution, in terms of optimal weights and state update rules, is derived by training each individual neuron to perform either kernel classifica ...

Bottom-up models of functionally relevant patterns of neural activity provide an explicit link between neuronal dynamics and computation. A prime example of functional activity patterns are propagating bursts of place-cell activities called hippocampal rep ...

This manuscript serves a specific purpose: to give readers from fields such as material science, chemistry, or electronics an overview of implementing a reservoir computing (RC) experiment with her/his material system. Introductory literature on the topic ...

This thesis consists of three applications of machine learning techniques to empirical asset pricing. In the first part, which is co-authored work with Oksana Bashchenko, we develop a new method that detects jumps nonparametrically in financial time series ...

Neural computational power is determined by neuroenergetics, but how and which energy substrates are allocated to various forms of memory engram is unclear. To solve this question, we asked whether neuronal fueling by glucose or lactate scales differently ...

Demand forecasting is becoming increasingly important as firms launch new products with short life cycles more frequently. This paper provides a framework based on state-of-the-art techniques that enables firms to use quantitative methods to forecast sales ...

Side-channel attacks constitute a concrete threat to IoT systems-on-a-chip (SoCs). Embedded memories implemented with 6T SRAM macrocells often dominate the area and power consumption of these SoCs. Regardless of the computational platform, the side-channel ...

Over the past few years, there has been an increase in the use of chatbots for educational purposes. Nevertheless, the chatbot technologies and architectures that are often applied to educational contexts are not necessarily designed for such contexts. Whi ...

Remote sensing visual question answering (RQA) was recently proposed with the aim of interfacing natural language and vision to ease the access of information contained in Earth Observation data for a wide audience, which is granted by simple questions in ...

In the present work, we approach two key aspects of memory formation: associative memory and synaptic consolidation. The storage of associative memory is commonly related to the medial temporal lobe in humans. Experimental evidence shows that the memories ...

Sleep favors the reactivation and consolidation of newly acquired memories. Yet, how our brain selects the noteworthy information to be reprocessed during sleep remains largely unknown. From an evolutionary perspective, individuals must retain information ...

Recent developments in speech emotion recognition (SER) often leverage deep neural networks (DNNs). Comparing and benchmarking different DNN models can often be tedious due to the use of different datasets and evaluation protocols. To facilitate the proces ...

Memory-Based Model Editing at Scale

Chat with Graph Search

Structure-preserving approaches and data-driven closure modeling for model order reduction

Epigenetic plasticity as a signature for memory allocation

Hypothalamic pregnenolone mediates recognition memory in the context of metabolic disorders

Kernel Memory Networks: A Unifying Framework for Memory Modeling

Mesoscopic description of hippocampal replay and metastability in spiking neural networks with short-term plasticity

Hands-on reservoir computing: a tutorial for practical implementation

Essays in Empirical Asset Pricing

Lactate supply overtakes glucose when neural computational and cognitive loads scale up

A Machine Learning-based Framework for Forecasting Sales of New Products With Short Life Cycles Using Deep Neural Networks

Low-Cost Side-Channel Secure Standard 6T-SRAM-Based Memory With a 1% Area and Less Than 5% Latency and Power Overheads

A Blueprint for Integrating Task-Oriented Conversational Agents in Education

Prompt–RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering

A dynamical systems approach to synaptic consolidation and associations of concepts in hippocampus

Reward biases spontaneous neural reactivation during sleep

Serab: A Multi-Lingual Benchmark For Speech Emotion Recognition