The paper improves CNN visualization for safer reinforcement learning.
problem Safety risks in reinforcement learning control systems.
method Extensions of CNN visualization algorithms for reinforcement learning.
result Visualization aids in understanding and improving reinforcement learning policies.
Introspection Learning asks policies introspective questions to improve learning.
problem Improving reinforcement learning efficiency and robustness.
method Synthesizes experience through direct policy introspection without interaction.
result Demonstrates improved training speed and robustness.
This paper explores intrinsic rewards to improve learning from multiple value functions.
problem How to adapt reinforcement learning systems to optimize learning from multiple value functions.
method Investigated and compared 14 different intrinsic reward mechanisms in a new bandit-like parallel-learning testbed.
result Intrinsic rewards based on the amount of learning can generate useful behavior, if each individual learner is introspective.
Proposes a technique to interpret deep learning models by generating counterfactual inputs.
problem Understanding and explaining the decisions made by deep neural networks.
method Uses a generative model to edit input images and generate counterfactual scenarios for model interpretation.
result Demonstrates the effectiveness of the introspection approach on MNIST and CelebA datasets.
Detects misclassifications and adversarial examples using neural network logits.
problem Unable to detect misclassifications and adversarial examples in neural networks.
method Introspection using pretrained neural network logits.
result Simple 3-layer neural network trained on logits detects misclassifications competitively.
Introspects convolutional speech recognition models using Gradient-adjusted Neuron Activation Profiles.
problem Lack of interpretability in deep learning ASR models.
method Gradient-adjusted Neuron Activation Profiles (GradNAPs) for feature and representation visualization.
result Gains insight into how data is processed in convolutional ASR models.
The paper proposes a method to calibrate healthcare AI models for reliability and interpretability.
problem Characterizing model reliability and enabling introspection of model behavior in clinical decision making.
method A calibration-driven learning method combined with interpretability techniques based on counterfactual reasoning.
result Demonstrates the effectiveness of the proposed approach using a lesion classification problem with dermoscopy images.
The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation. We present the Neural Photo Editor, an interface that leverages the power of generative neural networks to make large, semantically coherent changes to existing images. To tackle…
IntroVAE synthesizes high-quality photos by self-evaluating and improving its outputs.
problem Generating high-quality photographic images with stable and realistic results.
method Introspective Variational Autoencoder (IntroVAE) that trains inference and generator models jointly, encouraging the inference model to distinguish between generated and real samples.
result Produces high-resolution photo-realistic images comparable to or better than state-of-the-art GANs.
RPO uses past and future state-action info for better policy optimization.
problem Sample inefficiency in on-policy reinforcement learning methods.
method Reflective Policy Optimization (RPO) integrates past and future state-action info for policy improvement.
result RPO improves policy performance and contracts the solution space, leading to faster convergence.
RE enhances DL by learning model behavior, enabling iterative self-improvement.
problem Static data representations limit DL's potential for evolving models.
method RE uses multiple mappings of data through identical deep architectures, analyzing internal representations and performance signals.
result Models can gain insight from predecessors, leading to iterative self-improvement.
This work improves motion planning for quadcopters by learning and reasoning about controller performance.
problem Improving motion planning for quadcopters with safety margins and execution reliability.
method Introspective learning and reasoning to correct execution bias and improve collision checking.
result Substantial reduction in safety margins for motion actions, leading to safer execution.
Explains agent behavior through intended outcomes in reinforcement learning.
problem Proving impossibility of general post-hoc explanations in reinforcement learning.
method Derives local explanations based on intention for Q-function approximations, proving consistency with learned Q-values.
result Demonstrates the necessity of collecting information during training for accurate explanations.
ISP improves DNN uncertainty for better subgroup accuracy.
problem Improving accuracy-group robustness in deep neural networks.
method Introspective Self-play (ISP) adds an introspection task to improve bias-awareness and uncertainty.
result ISP improves the accuracy-group robustness trade-off of AL methods.
IntroVAC learns interpretable latent subspaces for better image quality.
problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.
The paper proposes a method to explain expert decisions by modeling preferences with 'what if' outcomes.
problem Interpreting and auditing decision-making policies in institutions.
method Integrating counterfactual reasoning into batch inverse reinforcement learning.
result The method effectively recovers accurate and interpretable descriptions of expert behavior.
EPIC quantifies reward differences without policy optimization.
problem Distinguishing reward function quality from policy optimization issues.
method EPIC distance to compare reward functions directly.
result EPIC bounds policy training success and regret.
Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and malware detection. In these contexts, model interpretability is vital for administ…
Painless Activation Steering automates post-training for LMs without manual intervention.
problem Manual post-training methods are time-consuming and labor-intensive.
method Painless Activation Steering (PAS) is a fully automated approach that requires no manual intervention.
result PAS reliably improves performance for behavior tasks but not for intelligence-oriented tasks.
This review synthesizes uncertainty modeling in probabilistic image segmentation.
problem Relaxed Bayesian assumptions lead to missing uncertainty information in deep models.
method Standardizes theory, notation, and terminology for feature- and parameter-distribution modeling.
result Establishes a common framework for robust decision-making in segmentation tasks.
Whole MILC learns brain disorder dynamics from unlabeled data.
problem Learning spatio-temporal brain disorder dynamics from unlabeled data.
method Self-supervised pre-training of whole MILC on unlabeled healthy control data.
result Whole MILC outperforms existing methods and provides diagnostic insights.
Vizarel aims to help RL agents by visualizing their performance.
problem Existing visualization tools are not suitable for reinforcement learning.
method Designing a prototype system for interpreting RL agent performance.
result Prototype system identified features for visualizing RL agent performance.
End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory, throughput and training data. We conduct several systematic experiments adapting a Wa…
DSS networks use scale-equivariant cross-correlations to improve image recognition.
problem Improving image recognition by exploiting scale invariance.
method Constructing scale-equivariant cross-correlations based on scale-spaces and semigroups.
result Demonstrated utility on Patch Camelyon and Cityscapes datasets.
Modular networks learn to decompose neural computation efficiently.
problem Efficiently scaling model capacity in deep learning.
method End-to-end learning of neural modules and their decomposition based on data.
result Superior performance in image recognition and language modeling tasks.
Interactive tool helps RL researchers debug and understand their models.
problem Challenges in debugging reinforcement learning algorithms.
method Design and implementation of an interactive visualization tool.
result Addresses features missing from previous tools for RL.
Paper introduces a method to interpret complex epidemiology simulators.
problem Difficult interpretation of stochastic epidemiology simulators.
method Hijacking internal random number generators with probabilistic programming.
result Restores trust between policymakers and simulators by providing insights.
VSML unifies meta learning concepts and enables simple backpropagation.
problem Improving and unifying meta learning concepts for neural networks.
method Unified approach using variable shared meta learning and simple weight-sharing.
result Simple backpropagation can be implemented and meta learned without gradient calculation.
Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain func…
Semantic embeddings improve safety-critical classifier performance.
problem Improving interpretability and error detection in safety-critical neural networks.
method Created embeddings from symbolic domain knowledge, used for misprediction interpretation and error detection, introduced semantic distance for confidence measurement.
result Semantic distance achieves near state-of-the-art performance in a traffic sign classifier, faster than other methods.
Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system's inner-workings. This paper proposes a neu…
SoftAdapt dynamically adjusts loss weights for multi-part functions.
problem Slow convergence and poor weight selection for multi-part loss functions.
method SoftAdapt dynamically changes weights based on live performance statistics.
result Improved convergence and better weight selection for multi-part loss functions.
Method uses network biology to construct gene expression models for cancer.
problem Building models for cancer phenotypes using gene expression data.
method Unsupervised construction of computational graphs based on protein-protein networks.
result The method outperforms other models in cancer phenotype analysis.
System predicts respiratory failure up to 8 hours early.
problem Early detection of respiratory failure in ICU patients.
method Machine learning on ICU patient monitoring data.
result System outperforms traditional clinical decision-making.
Data-driven spatial filtering algorithms optimize scores such as the contrast between two conditions to extract oscillatory brain signal components. Most machine learning approaches for filter estimation, however, disregard within-trial temporal dynamics and are extremely sensitive to changes in training data and invol…
Active inference selects actions to maximize information gain, aiding structure learning.
problem Learning the structure of underlying world models.
method Active inference selects actions based on expected free energy, which includes information gain and value.
result Actions that maximize information gain help disambiguate among alternative models.
Compact Gaussian model approximates deep ensemble predictions.
problem Efficiently approximating deep ensemble models for image prediction.
method Sparse-structured multivariate Gaussian with Cholesky parameterization trained to match pre-trained ensemble outputs.
result Compact representation captures uncertainty and structured correlations explicitly.
Dragonfly optimizes complex functions without needing grad students.
problem Challenging real-world optimisation tasks where conventional BO methods fail.
method Scalable and robust Bayesian Optimisation with multiple advanced methods.
result Significant improvements in BO performance when integrating new methods.
This paper explores neural networks for colorizing grayscale images.
problem Colorizing grayscale images using neural networks.
method Comparison of existing and novel generative models (CVAE, CWGAN-GP, AGE, IVAE) trained on CIFAR-10 images.
result CVAE with L1 reconstruction loss and IVAE achieve the highest Inception Score (IS).
New ML framework for reliable and explainable material predictions.
problem Challenges in applying ML to materials science, especially with imbalanced data.
method Proposes a general-purpose explainable and reliable machine-learning framework using ensembles of simpler models.
result Demonstrates improved reliability and explainability in material property predictions.
Model captures neural activity related to behavior while separating internal computations.
problem Capturing neural activity related to behavior from complex brain recordings.
method Behavior-decomposed linear dynamical systems (b-dLDS) model.
result Improves over state-of-the-art models in disentangling behavior-related dynamics.
Behavior modification improves prediction accuracy by nudging user behavior.
problem Improving prediction accuracy using behavior modification techniques.
method Combining prediction and behavior modification with reinforcement learning algorithms.
result Behavior modification can make predictions more certain but may not generalize.
Paper presents a new time-series segmentation technique for mobile phone user behavior.
problem Current segmentation techniques do not accurately capture individual user behavior over time.
method Behavior-Oriented Time Segmentation (BOTS) technique that considers temporal coverage and number of incidences.
result BOTS technique better captures user behavior at various times of day and week.
LISBET automates social behavior analysis using machine learning.
problem Manual annotation of social behaviors is time-consuming, biased, and misses subtle interactions.
method Self-supervised learning on body tracking data.
result Automated detection and segmentation of social interactions.
The paper introduces new metrics for evaluating generative models of behavior.
problem Lack of quantitative evaluation criteria for unsupervised behavior discovery.
method Proposed and investigated several metrics for generative models of behavior.
result The proposed metrics correspond with biologists' intuitions and allow for model evaluation and bias understanding.
Proposes a graph-based system for personalized news recommendation considering multiple user behaviors.
problem Lack of considering multiple user behaviors in news recommendation systems.
method Builds an interaction behavior graph, applies DeepWalk and G-CNN for news and behavior sequence representations, introduces core and coritivity features.
result Achieves personalized news recommendation considering user's concentration degree of interests.
Study reveals LLM personality patterns but lacks behavioral consistency.
problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.
Herd behavior is an important economic phenomenon, especially in the context of the recent financial crises. In this paper, herd behavior in global stock markets is investigated with a focus on intercontinental comparison. Since most existing herd behavior indices do not provide a comparative method, we propose a new h…