Search Results for author:
Found 11 papers, 3 papers with code
Multi-Agent Dynamic Pricing in a Blockchain Protocol Using Gaussian Bandits
The Graph Protocol indexes historical blockchain transaction data and makes it available for querying.
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
Dialog State Tracking (DST) is one of the most crucial modules for goal-oriented dialogue systems.
Transfer Learning in Visual and Relational Reasoning
Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce.
PyTorchPipe: a framework for rapid prototyping of pipelines combining language and vision
The paper introduces PyTorchPipe (PTP), a framework built on top of PyTorch.
Leveraging Medical Visual Question Answering with Supporting Facts
In this working notes paper, we describe IBM Research AI (Almaden) team's participation in the ImageCLEF 2019 VQA-Med competition.
On transfer learning using a MAC model variant
We introduce a variant of the MAC model (Hudson and Manning, ICLR 2018) with a simplified set of equations that achieves comparable accuracy, while training faster.
Using Multi-task and Transfer Learning to Solve Working Memory Tasks
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology.
Learning to Remember, Forget and Ignore using Attention Control in Memory
Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans.
Object-based reasoning in VQA
Visual Question Answering (VQA) is a novel problem domain where multi-modal inputs must be processed in order to solve the task given in the form of a natural language.
Surprisal-Driven Zoneout
We propose a novel method of regularization for recurrent neural networks called suprisal-driven zoneout.
Utilization of Deep Reinforcement Learning for saccadic-based object visual search
The paper focuses on the problem of learning saccades enabling visual object search.
