Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms used in computer vision. However, these models often suffer from the lack of interpretability of their information transformation process. To address this problem, we introduce a novel model called Sparse Deep Predictive Coding (SDPC). In a biologically realistic manner, SDPC mimics how the brain is efficiently representing visual information. This model complements the hierarchical convolutional layers found in CNNs with the feed-forward and feed-back update scheme described in the Predictive Coding (PC) theory and found in the architecture of the mammalian visual system. We experimentally demonstrate on two databases that the SDPC model extracts qualitatively meaningful features. These features, besides being similar to some of the biological Receptive Fields of the visual cortex, also represent hierarchically independent components of the image that are crucial to describe it in a generic manner. For the first time, the SDPC model demonstrates a meaningful representation of features within the hierarchical generative model and of the decision-making process leading to a specific prediction. A quantitative analysis reveals that the features extracted by the SDPC model encode the input image into a representation that is both easily classifiable and robust to noise.

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients in extensive experiments on a new synthetic number guessing game. Moreover, in a real-word visual object discovery game, the proposed method is twice as sample-efficient as policy gradients and shows state-of-the-art performance.

In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised learning, but has not yet been thoroughly researched in RL. To address this problem, we propose a novel Curiosity-Driven Prioritization (CDP) framework to encourage the agent to over-sample those trajectories that have rare achieved goal states. The CDP framework mimics the human learning process and focuses more on relatively uncommon events. We evaluate our methods using the robotic environment provided by OpenAI Gym. The environment contains six robot manipulation tasks. In our experiments, we combined CDP with Deep Deterministic Policy Gradient (DDPG) with or without Hindsight Experience Replay (HER). The experimental results show that CDP improves both performance and sample-efficiency of reinforcement learning agents, compared to state-of-the-art methods.

We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual question answering, our probabilistic formulation offers two key conceptual advantages over prior neural-symbolic models for VQA. Firstly, the programs generated by our model are more understandable while requiring lesser number of teaching examples. Secondly, we show that one can pose counterfactual scenarios to the model, to probe its beliefs on the programs that could lead to a specified answer given an image. Our results on the CLEVR and SHAPES datasets verify our hypotheses, showing that the model gets better program (and answer) prediction accuracy even in the low data regime, and allows one to probe the coherence and consistency of reasoning performed.

Recent advances in deep learning motivate the use of deep neural networks in Internet-of-Things (IoT) applications. These networks are modelled after signal processing in the human brain, thereby leading to significant advantages at perceptual tasks such as vision and speech recognition. IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain. This observation leads to a fundamental question: For IoT applications, can one develop a new brand of neural network structures that synthesize features inspired not only by the biology of human perception but also by the fundamental nature of physics? Hence, in this paper, instead of using conventional building blocks (e.g., convolutional and recurrent layers), we propose a new foundational neural network building block, the Short-Time Fourier Neural Network (STFNet). It integrates a widely-used time-frequency analysis method, the Short-Time Fourier Transform, into data processing to learn features directly in the frequency domain, where the physics of underlying phenomena leave better foot-prints. STFNets bring additional flexibility to time-frequency analysis by offering novel nonlinear learnable operations that are spectral-compatible. Moreover, STFNets show that transforming signals to a domain that is more connected to the underlying physics greatly simplifies the learning process. We demonstrate the effectiveness of STFNets with extensive experiments. STFNets significantly outperform the state-of-the-art deep learning models in all experiments. A STFNet, therefore, demonstrates superior capability as the fundamental building block of deep neural networks for IoT applications for various sensor inputs.

INIMALLY invasiveprocedures in the head and neck, e. g. functional endoscopic sinus surgery, typically employ surgical navigation systems to provide surgeons with additional anatomical and positional information. This helps them avoid critical structures, such as the brain, eyes, and major arteries, that are spatially close to the sinus cavities and must not be disturbed during surgery. Computer vision-based navigation systems that rely on the intra-operative endoscopic video stream and do not introduce additional hardware are both easy to integrate into clinical workflow and cost-effective. Such systems generally require registration of preoperative data, such as CT scans or statistical models, to the intraoperative videodata [1], [2], [3], [4]. This registration must be highly accurate in order to guarantee reliable performance of the navigation system. To enable an accurate registration, a feature-based video-CT registration algorithm requires accurate andsufficiently dense intra-operative 3D reconstructions of the anatomy from endoscopic videos.

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward functions and goal states have been used to communicate objectives. But people can communicate objectives to each other simply by describing or demonstrating them. How can we build learning algorithms that will allow us to tell machines what we want them to do? In this work, we investigate the problem of grounding language commands as reward functions using inverse reinforcement learning, and argue that language-conditioned rewards are more transferable than language-conditioned policies to new environments. We propose language-conditioned reward learning (LC-RL), which grounds language commands as a reward function represented by a deep neural network. We demonstrate that our model learns rewards that transfer to novel tasks and environments on realistic, high-dimensional visual environments with natural language commands, whereas directly learning a language-conditioned policy leads to poor performance.

Stochastic bandit algorithms can be used for challenging non-convex optimization problems. Hyperparameter tuning of neural networks is particularly challenging, necessitating new approaches. To this end, we present a method that adaptively partitions the combined space of hyperparameters, context, and training resources (e.g., total number of training iterations). By adaptively partitioning the space, the algorithm is able to focus on the portions of the hyperparameter search space that are most relevant in a practical way. By including the resources in the combined space, the method tends to use fewer training resources overall. Our experiments show that this method can surpass state-of-the-art methods in tuning neural networks on benchmark datasets. In some cases, our implementations can achieve the same levels of accuracy on benchmark datasets as existing state-of-the-art approaches while saving over 50% of our computational resources (e.g. time, training iterations).

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a function $f$, a point $x$, and the gradient $\nabla_x f$ of $f$, we aim to find the step-size $h$ which is (locally) optimal, i.e. satisfies: $$ h=arg\,min_{t \geq 0} f(x-t \nabla_x f). $$ Making use of quadratic approximation, we show that the algorithm satisfies the above assumption. We experimentally show that our method is insensitive to the choice of initial learning rate while achieving results comparable to other methods.

Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, we evaluate both random search with early-stopping and a novel random search with weight-sharing algorithm on two standard NAS benchmarks---PTB and CIFAR-10. Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS, a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Finally, we explore the existing reproducibility issues of published NAS results. We note the lack of source material needed to exactly reproduce these results, and further discuss the robustness of published results given the various sources of variability in NAS experimental setups. Relatedly, we provide all information (code, random seeds, documentation) needed to exactly reproduce our results, and report our random search with weight-sharing results for each benchmark on two independent experimental runs.