Search Results for author:
Found 22 papers, 3 papers with code
Error Causal inference for Multi-Fusion models
In this paper, we propose an error causal inference method that could be used for finding dominant features for a faulty instance under a well-trained multi-modality input model, which could apply to any testing instance.
Mistake Captioning: A Machine Learning Approach for Detecting Mistakes and Generating Instructive Feedback
Giving feedback to students is not just about marking their answers as correct or incorrect, but also finding mistakes in their thought process that led them to that incorrect answer.
Machine Learning Approaches for Principle Prediction in Naturally Occurring Stories
To do this, we extend a dataset that has been previously used to train a binary normative classifier with annotations of moral principles.
StyleM: Stylized Metrics for Image Captioning Built with Contrastive N-grams
In this paper, we build two automatic evaluation metrics for evaluating the association between a machine-generated caption and a ground truth stylized caption: OnlyStyle and StyleCIDEr.
Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand
We found that using our proposed method, agents are able to swiftly change their course of action according to the changes in demand, and they also engage in collusive behavior in many simulations.
Modelling Cournot Games as Multi-agent Multi-armed Bandits
We investigate the use of a multi-agent multi-armed bandit (MA-MAB) setting for modeling repeated Cournot oligopoly games, where the firms acting as agents choose from the set of arms representing production quantity (a discrete value).
A Self-Explainable Stylish Image Captioning Framework via Multi-References
In this paper, we propose to build a stylish image captioning model through a Multi-style Multi modality mechanism (2M).
Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior
As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior or cause harm.
Influencing Reinforcement Learning through Natural Language Guidance
In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known Interactive reinforcement learning technique.
3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model
In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap.
Multi-agent Reinforcement Learning for Decentralized Stable Matching
Along with conventional stable matching case where agents have strictly ordered preferences, we check the applicability of our approach for stable matching with incomplete lists and ties.
Visual Question Answering Using Semantic Information from Image Descriptions
In this work, we propose a deep neural architecture that uses an attention mechanism which utilizes region based image features, the natural language question asked, and semantic knowledge extracted from the regions of an image to produce open-ended answers for questions asked in a visual question answering (VQA) task.
Learning Norms from Stories: A Prior for Value Aligned Agents
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans.
A Hierarchical Approach for Visual Storytelling Using Image Description
One of the primary challenges of visual storytelling is developing techniques that can maintain the context of the story over long event sequences to generate human-like stories.
Monte-Carlo Tree Search for Simulation-based Strategy Analysis
Using these case studies, we show how using simulated agents to model humans of varying skill levels allows us to extract metrics to describe game balance (in the case of Scrabble) and highlight potential design flaws (in the case of Cardonomicon).
Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
The second study further explores user preferences between the generated rationales with regard to confidence in the autonomous agent, communicating failure and unexpected behavior.
Controllable Neural Story Plot Generation via Reward Shaping
Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story.
Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback.
Guiding Reinforcement Learning Exploration Using Natural Language
We then use this learned model to guide agent exploration using a modified version of policy shaping to make it more effective at learning in unseen environments.
Event Representations for Automated Story Generation with Deep Neural Nets
We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence).
Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch.
Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.
