Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning

Abstract

We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or few-short learning. Data-driven deep learning models have achieved remarkable performance and demonstrated capabilities surpassing human experts in many applications. Yet, their inability to exploit domain knowledge leads to serious performance limitations in practical applications. In particular, deep learning systems are exposed to adversarial attacks, which can trick them into making glaringly incorrect decisions. Moreover, complex data-driven models typically lack interpretability or explainability, i.e., their decisions cannot be understood by human subjects. Furthermore, models are usually trained on standard datasets with a closed-world assumption. Hence, they struggle to generalize to unseen cases during inference in practical open-world environments, thus, raising the zero- or few-shot generalization problem. Although many conventional solutions exist, explicit domain knowledge, brain-inspired neural network and cognitive architectures offer powerful new dimensions towards alleviating these problems. Prior knowledge is represented in appropriate forms and incorporated in deep learning frameworks to improve performance. Brain-inspired cognition methods use computational models that mimic the human mind to enhance intelligent behavior in artificial agents and autonomous robots. Ultimately, these models achieve better explainability, higher adversarial robustness and data-efficient learning, and can, in turn, provide insights for cognitive science and neuroscience-that is, to deepen human understanding on how the brain works in general, and how it handles these problems.

References in corpus (33)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Training language models to follow instructions with human feedback
• Learning to Prompt for Vision-Language Models
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graphs
• Large Language Models are Zero-Shot Reasoners
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• VL-BERT: Pre-training of Generic Visual-Linguistic Representations
• Evaluation of Output Embeddings for Fine-Grained Image Classification
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• "Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
• Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
• DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
• Logic Explained Networks
• Ontology-enhanced Prompt-tuning for Few-shot Learning
• When Explanations Lie: Why Many Modified BP Attributions Fail
• Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
• Mind Reader: Reconstructing complex images from brain activities
• Associative Memories via Predictive Coding
• Multimodal neural networks better explain multivoxel patterns in the hippocampus
• Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
• Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations
• Improving Certified Robustness via Statistical Learning with Logical Reasoning
• VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives