相关论文: A Minimal Intervention Definition of Reverse Engin…
Microcode is an abstraction layer on top of the physical components of a CPU and present in most general-purpose CPUs today. In addition to facilitate complex and vast instruction sets, it also provides an update mechanism that allows CPUs…
A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition covers first-order logical inference or probabilistic inference. It also includes…
Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain level of input…
Addressing complex societal challenges, such as improving public health, fostering honesty in workplaces, or encouraging eco-friendly behaviour requires effective nudges to influence human behaviour at scale. Intervention science seeks to…
With the advent of high-throughput profiling methods, interest in reverse engineering the structure and dynamics of biochemical networks is high. Recently an algorithm for reverse engineering of biochemical networks was developed by…
Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small neural…
The computational underpinnings of positive psychotic symptoms have recently received significant attention. Candidate mechanisms include some combination of maladaptive priors and reduced updating of these priors during perception. A…
Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…
One of the central problems in neuroscience is reconstructing synaptic connectivity in neural circuits. Synapses onto a neuron can be probed by sequentially stimulating potentially pre-synaptic neurons while monitoring the membrane voltage…
NeurIPS 2020 requested that research paper submissions include impact statements on "potential nefarious uses and the consequences of failure." However, as researchers, practitioners and system designers, a key challenge to anticipating…
Machine learning has become mainstream across industries. Numerous examples proved the validity of it for security applications. In this work, we investigate how to reverse engineer a neural network by using only power side-channel…
Neurofeedback is a form of brain training in which subjects are fed back information about some measure of their brain activity which they are instructed to modify in a way thought to be functionally advantageous. Over the last twenty…
The ultimate goal of cognitive neuroscience is to understand the mechanistic neural processes underlying the functional organization of the brain. Key to this study is understanding structure of both the structural and functional…
In spite of intense research efforts, deep neural networks remain vulnerable to adversarial examples: an input that forces the network to confidently produce incorrect outputs. Adversarial examples are typically generated by an attack…
This is the first in a series of connected papers discussing the problem of a dynamically reconfigurable universal learning neurocomputer that could serve as a computational model for the whole human brain. The whole series is entitled "The…
From logical reasoning to mental simulation, biological and artificial neural systems possess an incredible capacity for computation. Such neural computers offer a fundamentally novel computing paradigm by representing data continuously and…
In this paper we present a foundational study on a constrained method that defines learning problems with Neural Networks in the context of the principle of least cognitive action, which very much resembles the principle of least action in…
This work describes a methodology to combine logic-based systems and connectionist systems. Our approach uses finite truth valued {\L}ukasiewicz logic, where we take advantage of fact what in this type of logics every connective can be…
Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…
Neurological diseases and injuries present some of the greatest challenges in modern medicine, often causing irreversible and lifelong burdens in the people whom they afflict. These diagnoses have devastating consequences on millions of…