Related papers: Shaping representations through communication: com…
The processes leading to change in languages are manifold. In order to reduce ambiguity in the transmission of information, agreement on a set of conventions for recurring problems is favored. In addition to that, speakers tend to use…
Deep learning methods capable of handling relational data have proliferated over the last years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these deep learning methods…
We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient information of an edit and can be used to apply edits to new inputs.…
We examine the effects of instantiating Lewis signaling games within a population of speaker and listener agents with the aim of producing a set of general and robust representations of unstructured pixel data. Preliminary experiments…
Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension…
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…
Social network structure is one of the key determinants of human language evolution. Previous work has shown that the network of social interactions shapes decentralized learning in human groups, leading to the emergence of different kinds…
While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…
Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…
As recent work demonstrated, the task of identifying communities in networks can be considered analogous to the classical problem of decoding messages transmitted along a noisy channel. We leverage this analogy to develop a community…
We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio…
Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…
Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…
The iterated learning model is an agent-based model of language evolution notable for demonstrating the emergence of compositional language. In its original form, it modelled language evolution along a single chain of teacher-pupil…
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…
Recent advancements in unsupervised feature learning have developed powerful latent representations of words. However, it is still not clear what makes one representation better than another and how we can learn the ideal representation.…
One significant simplification in most previous work on robot learning is the closed-world assumption where the robot is assumed to know ahead of time a complete set of predicates describing the state of the physical world. However, robots…
In an ego-network, an individual (ego) organizes its friends (alters) in different groups (social circles). This social network can be efficiently analyzed after learning representations of the ego and its alters in a low-dimensional, real…
We give an algorithm that learns a representation of data through compression. The algorithm 1) predicts bits sequentially from those previously seen and 2) has a structure and a number of computations similar to an autoencoder. The…