Learning sparse and meaningful representations through embodiment

The neuroconnectionist research programme

Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have been not only lauded as the current best models of information processing in the brain but also criticized for failing to account for basic cognitive functions. In this Perspective article, we propose that arguing about the successes and failures of a restricted set of current ANNs is the wrong approach to assess the promise of neuroconnectionism for brain science. Instead, we take inspiration from the philosophy of science, and in particular from Lakatos, who showed that the core of a scientific research programme is often not directly falsifiable but should be assessed by its capacity to generate novel insights. Following this view, we present neuroconnectionism as a general research programme centred around ANNs as a computational language for expressing falsifiable theories about brain computation. We describe the core of the programme, the underlying computational framework and its tools for testing specific neuroscientific hypotheses and deriving novel understanding. Taking a longitudinal view, we review past and present neuroconnectionist projects and their responses to challenges and argue that the research programme is highly progressive, generating new and otherwise unreachable insights into the workings of the brain.

Mutual influence between language and perception in multi-agent communication games

Language interfaces with many other cognitive domains. This paper explores how interactions at these interfaces can be studied with deep learning methods, focusing on the relation between language emergence and visual perception. To model the emergence of language, a sender and a receiver agent are trained on a reference game. The agents are implemented as deep neural networks, with dedicated vision and language modules. Motivated by the mutual influence between language and perception in cognition, we apply systematic manipulations to the agents’ (i) visual representations, to analyze the effects on emergent communication, and (ii) communication protocols, to analyze the effects on visual representations. Our analyses show that perceptual biases shape semantic categorization and communicative content. Conversely, if the communication protocol partitions object space along certain attributes, agents learn to represent visual information about these attributes more accurately, and the representations of communication partners align. Finally, an evolutionary analysis suggests that visual representations may be shaped in part to facilitate the communication of environmentally relevant distinctions. Aside from accounting for co-adaptation effects between language and perception, our results point out ways to modulate and improve visual representation learning and emergent communication in artificial agents.

Language is grounded in the world and used to coordinate and achieve common objectives. We simulate grounded, interactive language use with a communication game. A sender refers to an object in the environment and if the receiver selects the correct object both agents are rewarded. By practicing the game, the agents develop their own communication protocol. We use this setup to study interactions between emerging language and visual perception. Agents are implemented as neural networks with dedicated vision modules to process images of objects. By manipulating their visual representations we can show how variations in perception are reflected in linguistic variations. Conversely, we demonstrate that differences in language are reflected in the agents’ visual representations. Our simulations mirror several empirically observed phenomena: labels for concrete objects and properties (e.g., “striped”, “bowl”) group together visually similar objects, object representations adapt to the categories imposed by language, and representational spaces between communication partners align. In addition, an evolutionary analysis suggests that visual representations may be shaped, in part, to facilitate communication about environmentally relevant information. In sum, we use communication games with neural network agents to model co-adaptation effects between language and visual perception. Future work could apply this computational framework to other interfaces between language and cognition.

Sparsity-control ternary weight networks

Deep neural networks (DNNs) have been widely and successfully applied to various applications, but they require large amounts of memory and computational power. This severely restricts their deployment on resource-limited devices. To address this issue, many efforts have been made on training low-bit weight DNNs. In this paper, we focus on training ternary weight {-1, 0, ＋1} networks which can avoid multiplications and dramatically reduce the memory and computation requirements. A ternary weight network can be considered as a sparser version of the binary weight counterpart by replacing some -1s or 1s in the binary weights with 0s, thus leading to more efficient inference but more memory cost. However, the existing approaches to train ternary weight networks cannot control the sparsity (i.e., percentage of 0s) of the ternary weights, which undermines the advantage of ternary weights. In this paper, we propose to our best knowledge the first sparsity-control approach (SCA) to train ternary weight networks, which is simply achieved by a weight discretization regularizer (WDR). SCA is different from all the existing regularizer-based approaches in that it can control the sparsity of the ternary weights through a controller α and does not rely on gradient estimators. We theoretically and empirically show that the sparsity of the trained ternary weights is positively related to α. SCA is extremely simple, easy-to-implement, and is shown to consistently outperform the state-of-the-art approaches significantly over several benchmark datasets and even matches the performances of the full-precision weight counterparts.