A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.
This paper analyzes the variability of Concept Activation Vectors (CAVs).
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated w…
Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.
In this paper we study a symmetry group of vector space. Basis manifold is a homogeneous space of a symmetry group. This concept leads us to the definition of active and passive transformations on basis manifold. Active transformation can be expressed as a transformation of vector space. Passive transformation gives ab…
Unified framework for testing deep learning models with concept activation vectors.
Active management is a term that has many meanings and we have found the defining characteristics needed for success as an "active manager" elusive within the literature. In this paper we offer a set of criteria that defines an active manager and his success. In order to facilitate this, we introduce several definition…
MCD offers a complete model understanding for high-stake decisions.
Researchers apply concept-based explainability to EEG data.
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
DeepStreamCE detects new classes in streaming deep neural networks.
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…
Deep learning skin lesion classifier explained using CAVs.
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active…
DORA analyzes deep neural networks' internal representations to detect spurious correlations.
We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…
New neural operators learn structured patterns efficiently.
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), whic…
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…
Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in th…
To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good p…
FASE-AL uses active learning to reduce labeling costs for data streams.
The goal of this article is to describe the concepts of system dynamics and its applications to the simulation modeling of financial institutions daily activity. The hybrid method of the re-engineering of banking business processes based upon combination of system dynamics, queuing theory and tools of ordinary differen…
Unified Bayesian model explains in-context learning and activation steering in LLMs.
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for building effective data-driven solutions. We develop an active learning framework for mining such relations subject to a strict order. Our a…
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically labels the majority of the datapoints, thus drastically reducing the human labeling b…
Paper revises power theory using classical mechanics concepts.
This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be…
A new indicator measures project risk from activity durations.
We address challenges of active learning under scarce informational resources in non-stationary environments. In real-world settings, data labeled and integrated into a predictive model may become invalid over time. However, the data can become informative again with switches in context and such changes may indicate un…
The paper benchmarks data stream classifiers for human activity recognition on connected devices.
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by querying users with preference questions. In this paper, we will develop a new al…
New algorithm for active learning from feedback coding.
In an effort to understand the meaning of the intermediate representations captured by deep networks, recent papers have tried to associate specific semantic concepts to individual neural network filter responses, where interesting correlations are often found, largely by focusing on extremal filter responses. In this …
CBMs improve interpretability in RUL prediction for aircraft engines.
Framework models supervised learning in non-stationary data.
Active inference uses machine learning to prioritize data labeling for more efficient statistical inference.
Efficiently selects nearest neighbors for labeling to speed up active learning.
The changing nature of the relationship between a retail bank and its customers is examined, particularly with respect to new financial concepts, debt and regulation. The traditional image of a bank is portrayed as a physical building a classical Doric portico. This image conveys concepts of service, soundness, strengt…
New approach improves human activity recognition with wearables.
Financial markets provide an ideal frame for studying decision making in crowded environments. Both the amount and accuracy of the data allows to apply tools and concepts coming from physics that studies collective and emergent phenomena or self-organised and highly heterogeneous systems. We analyse the activity of 29,…
Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …
In this paper, we consider adaptive decision-making problems for stochastic state estimation with partial observations. First, we introduce the concept of weak adaptive submodularity, a generalization of adaptive submodularity, which has found great success in solving challenging adaptive state estimation problems. The…
This work abstracts deep neural networks into concept graphs for better interpretability in medical tasks.
Efficiently learns reward functions with fewer queries and shorter computation times.
EAMDrift improves time series prediction accuracy by 20%.
In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activi…