Related papers: Curriculum Q-Learning for Visual Vocabulary Acquis…

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this…

Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the…

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet. Specifically, we learn a weight for each sample by…

In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is…

Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often…

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…

We explore different curriculum learning methods for training convolutional neural networks on the task of deformable pairwise 3D medical image registration. To the best of our knowledge, we are the first to attempt to improve performance…

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…

We investigate how neural language models acquire individual words during training, extracting learning curves and ages of acquisition for over 600 words on the MacArthur-Bates Communicative Development Inventory (Fenson et al., 2007).…

Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the…

Visual Question Answering (VQA) is a challenging multimodal task to answer questions about an image. Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context.…

Learning to lift and rotate objects with the fingertips is necessary for autonomous in-hand dexterous manipulation. In our study, we explore the impact of various factors on successful learning strategies for this task. Specifically, we…

Children efficiently acquire language not just by listening, but by interacting with others in their social environment. Conversely, large language models are typically trained with next-word prediction on massive amounts of text. Motivated…

Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard techniques of deep learning.…

ContextVis introduces a workflow by integrating generative models to create contextual learning materials. It aims to boost knowledge acquisition through the creation of resources with contextual cues. A case study on vocabulary learning…

Video object segmentation can be understood as a sequence-to-sequence task that can benefit from the curriculum learning strategies for better and faster training of deep neural networks. This work explores different schedule sampling and…

Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data. In this paper, we present a flexible audiovisual model that introduces a soft-clustering module…