Memory and attention in deep learning
It addresses the foundational challenge of memory construction for machine learning systems, aiming to improve their learning and acting capabilities, though it appears incremental by building on existing external memory approaches.
This thesis tackles the problem of advancing memory and attention mechanisms in deep learning to enhance machine intelligence, resulting in contributions such as new memory-augmented neural networks, improved memorization capacity, and simulation of a Universal Turing Machine.
Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn and act automatically just like human, memory construction for machine is inevitable. Artificial neural networks model neurons and synapses in the brain by interconnecting computational units via weights, which is a typical class of machine learning algorithms that resembles memory structure. Their descendants with more complicated modeling techniques (a.k.a deep learning) have been successfully applied to many practical problems and demonstrated the importance of memory in the learning process of machinery systems. Recent progresses on modeling memory in deep learning have revolved around external memory constructions, which are highly inspired by computational Turing models and biological neuronal systems. Attention mechanisms are derived to support acquisition and retention operations on the external memory. Despite the lack of theoretical foundations, these approaches have shown promises to help machinery systems reach a higher level of intelligence. The aim of this thesis is to advance the understanding on memory and attention in deep learning. Its contributions include: (i) presenting a collection of taxonomies for memory, (ii) constructing new memory-augmented neural networks (MANNs) that support multiple control and memory units, (iii) introducing variability via memory in sequential generative models, (iv) searching for optimal writing operations to maximise the memorisation capacity in slot-based memory networks, and (v) simulating the Universal Turing Machine via Neural Stored-program Memory-a new kind of external memory for neural networks.