Related papers: Why Do Animals Need Shaping? A Theory of Task Comp…

Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired to the target task.…

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…

Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement. One possibility is that neural networks implicitly break down complex tasks into…

Why does Deep Learning work? What representations does it capture? How do higher-order representations emerge? We study these questions from the perspective of group theory, thereby opening a new approach towards a theory of Deep learning.…

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief,…

Formation strategy is one of the most important parts of many multi-agent systems with many applications in real world problems. In this paper, a framework for learning this task in a limited domain (restricted environment) is proposed. In…

Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields including protein structural modeling. Protein structural modeling, such as predicting…

The main success stories of deep learning, starting with ImageNet, depend on deep convolutional networks, which on certain tasks perform significantly better than traditional shallow classifiers, such as support vector machines, and also…

Learning to solve sparse-reward reinforcement learning problems is difficult, due to the lack of guidance towards the goal. But in some problems, prior knowledge can be used to augment the learning process. Reward shaping is a way to…

Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more…

Learning and the ability to learn are important factors in development and evolutionary processes [1]. Depending on the level, the complexity of learning can strongly vary. While associative learning can explain simple learning behaviour…

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer. In control theory, prioritized composition is realized by null-space…

Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learning speed. This paper…

In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks that were previously assumed to require structured…

Motor adaptation displays a structure-learning effect: adaptation to a new perturbation occurs more quickly when the subject has prior exposure to perturbations with related structure. Although this `learning-to-learn' effect is well…

Animals can learn efficiently from a single experience and change their future behavior in response. However, in other instances, animals learn very slowly, requiring thousands of experiences. Here I survey tasks involving fast and slow…

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

In this paper, we make the case that a scientific theory of deep learning is emerging. By this we mean a theory which characterizes important properties and statistics of the training process, hidden representations, final weights, and…