Spiking neural networks (SNNs) with a lattice architecture are introduced in this work, combining several desirable properties of SNNs and self-organized maps (SOMs). Networks are trained with biologically motivated, unsupervised learning rules to obtain a self-organized grid of filters via cooperative and competitive excitatory-inhibitory interactions. Several inhibition strategies are developed and tested, such as (i) incrementally increasing inhibition level over the course of network training, and (ii) switching the inhibition level from low to high (two-level) after an initial training segment. During the labeling phase, the spiking activity generated by data with known labels is used to assign neurons to categories of data, which are then used to evaluate the network's classification ability on a held-out set of test data. Several biologically plausible evaluation rules are proposed and compared, including a population-level confidence rating, and an $n$-gram inspired method. The effectiveness of the proposed self-organized learning mechanism is tested using the MNIST benchmark dataset, as well as using images produced by playing the Atari Breakout game.

Cognitive and metacognitive strategy had demonstrated a significant role in self-regulated learning (SRL), and an appropriate use of strategies is beneficial to effective learning or question-solving tasks during a human-computer interaction process. This paper proposes a novel method combining Knowledge Map (KM) based data mining technique with Thinking Map (TM) to detect learner's cognitive and metacognitive strategy in the question-solving scenario. In particular, a graph-based mining algorithm is designed to facilitate our proposed method, which can automatically map cognitive strategy to metacognitive strategy with raising abstraction level, and make the cognitive and metacognitive process viewable, which acts like a reverse engineering engine to explain how a learner thinks when solving a question. Additionally, we develop an online learning environment system for participants to learn and record their behaviors. To corroborate the effectiveness of our approach and algorithm, we conduct experiments recruiting 173 postgraduate and undergraduate students, and they were asked to complete a question-solving task, such as "What are similarities and differences between array and pointer?" from "The C Programming Language" course and "What are similarities and differences between packet switching and circuit switching?" from "Computer Network Principle" course. The mined strategies patterns results are encouraging and supported well our proposed method.

We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset, VIST-Edit, includes 14,905 human edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.

Motion planning problems can be simplified by admissible projections of the configuration space to sequences of lower-dimensional quotient-spaces, called sequential simplifications. To exploit sequential simplifications, we present the Quotient-space Rapidly-exploring Random Trees (QRRT) algorithm. QRRT takes as input a start and a goal configuration, and a sequence of quotient-spaces. The algorithm grows trees on the quotient-spaces both sequentially and simultaneously to guarantee a dense coverage. QRRT is shown to be (1) probabilistically complete, and (2) can reduce the runtime by at least one order of magnitude. However, we show in experiments that the runtime varies substantially between different quotient-space sequences. To find out why, we perform an additional experiment, showing that the more narrow an environment, the more a quotient-space sequence can reduce runtime.

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit regularization of gradient descent over deep linear neural networks for matrix completion and sensing, a model referred to as deep matrix factorization. Our first finding, supported by theory and experiments, is that adding depth to a matrix factorization enhances an implicit tendency towards low-rank solutions, oftentimes leading to more accurate recovery. Secondly, we present theoretical and empirical arguments questioning a nascent view by which implicit regularization in matrix factorization can be captured using simple mathematical norms. Our results point to the possibility that the language of standard regularizers may not be rich enough to fully encompass the implicit regularization brought forth by gradient-based optimization.

Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence. This ability is thought to arise in the brain from computations implemented by bottom-up, horizontal, and top-down connections between neurons. However, the relative contributions of these connections to perceptual grouping are poorly understood. We address this question by systematically evaluating neural network architectures featuring combinations of these connections on two synthetic visual tasks, which stress low-level "gestalt" vs. high-level object cues for perceptual grouping. We show that increasing the difficulty of either task strains learning for networks that rely solely on bottom-up processing. Horizontal connections resolve this limitation on tasks with gestalt cues by supporting incremental spatial propagation of activities, whereas top-down connections rescue learning on tasks featuring object cues by propagating coarse predictions about the position of the target object. Our findings disassociate the computational roles of bottom-up, horizontal and top-down connectivity, and demonstrate how a model featuring all of these interactions can more flexibly learn to form perceptual groups.

In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment. However, comparing models in a real-world environment for the purposes of early stopping or hyperparameter tuning is costly and often practically infeasible. This leads us to examine off-policy policy evaluation (OPE) in such settings. We focus on OPE for value-based methods, which are of particular interest in deep RL, with applications like robotics, where off-policy algorithms based on Q-function estimation can often attain better sample complexity than direct policy optimization. Existing OPE metrics either rely on a model of the environment, or the use of importance sampling (IS) to correct for the data being off-policy. However, for high-dimensional observations, such as images, models of the environment can be difficult to fit and value-based methods can make IS hard to use or even ill-conditioned, especially when dealing with continuous action spaces. In this paper, we focus on the specific case of MDPs with continuous action spaces and sparse binary rewards, which is representative of many important real-world applications. We propose an alternative metric that relies on neither models nor IS, by framing OPE as a positive-unlabeled (PU) classification problem with the Q-function as the decision function. We experimentally show that this metric outperforms baselines on a number of tasks. Most importantly, it can reliably predict the relative performance of different policies in a number of generalization scenarios, including the transfer to the real-world of policies trained in simulation for an image-based robotic manipulation task.

Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients. We validate the empirical performance of the proposed idea on both low and high dimensional problems. The experimental results demonstrate the advantages of our approach for tuning high dimensional hyperparameters in machine learning.

Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of polynomial inequalities. We adopt the framework of semi-algebraic proof systems that manipulate polynomial inequalities via elementary inference rules that infer new inequalities from the premises. These proof systems are known to be very powerful, but searching for proofs remains a major difficulty. In this work, we introduce a machine learning based method to search for a dynamic proof within these proof systems. We propose a deep reinforcement learning framework that learns an embedding of the polynomials and guides the choice of inference rules, taking the inherent symmetries of the problem as an inductive bias. We compare our approach with powerful and widely-studied linear programming hierarchies based on static proof systems, and show that our method reduces the size of the linear program by several orders of magnitude while also improving performance. These results hence pave the way towards augmenting powerful and well-studied semi-algebraic proof systems with machine learning guiding strategies for enhancing the expressivity of such proof systems.

Deep Learning has attracted considerable attention across multiple application domains, including computer vision, signal processing and natural language processing. Although quite a few single node deep learning frameworks exist, such as tensorflow, pytorch and keras, we still lack a complete processing structure that can accommodate large scale data processing, version control, and deployment, all while staying agnostic of any specific single node framework. To bridge this gap, this paper proposes a new, higher level framework, i.e. Nemesyst, which uses databases along with model sequentialisation to allow processes to be fed unique and transformed data at the point of need. This facilitates near real-time application and makes models available for further training or use at any node that has access to the database simultaneously. Nemesyst is well suited as an application framework for internet of things aggregated control systems, deploying deep learning techniques to optimise individual machines in massive networks. To demonstrate this framework, we adopted a case study in a novel domain; deploying deep learning to optimise the high speed control of electrical power consumed by a massive internet of things network of retail refrigeration systems in proportion to load available on the UK National Grid (a demand side response). The case study demonstrated for the first time in such a setting how deep learning models, such as Recurrent Neural Networks (vanilla and Long-Short-Term Memory) and Generative Adversarial Networks paired with Nemesyst, achieve compelling performance, whilst still being malleable to future adjustments as both the data and requirements inevitably change over time.