Designing agent that can autonomously discover and learn a diversity of structures and skills in unknown changing environments is key for lifelong machine learning. A central challenge is how to learn incrementally representations in order to progressively build a map of the discovered structures and re-use it to further explore. To address this challenge, we identify and target several key functionalities. First, we aim to build lasting representations and avoid catastrophic forgetting throughout the exploration process. Secondly we aim to learn a diversity of representations allowing to discover a "diversity of diversity" of structures (and associated skills) in complex high-dimensional environments. Thirdly, we target representations that can structure the agent discoveries in a coarse-to-fine manner. Finally, we target the reuse of such representations to drive exploration toward an "interesting" type of diversity, for instance leveraging human guidance. Current approaches in state representation learning rely generally on monolithic architectures which do not enable all these functionalities. Therefore, we present a novel technique to progressively construct a Hierarchy of Observation Latent Models for Exploration Stratification, called HOLMES. This technique couples the use of a dynamic modular model architecture for representation learning with intrinsically-motivated goal exploration processes (IMGEPs). The paper shows results in the domain of automated discovery of diverse self-organized patterns, considering as testbed the experimental framework from Reinke et al. (2019).
We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data stream, learning a growing number of features that persist over time even though the data is not stored or replayed. To solve the UPL problem we propose the Self-Taught Associative Memory (STAM) architecture. Layered hierarchies of STAM modules learn based on a combination of online clustering, novelty detection, forgetting outliers, and storing only prototypical features rather than specific examples. We evaluate STAM re…
Golisano College of Computing and Information Sciences（戈利萨诺计算与信息科学学院）；Rochester Institute of Technology（罗切斯特理工学院）
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all factors of variations for top-down generation is compromised. Motivated by the concept of "starting small", we present a strategy to progressively learn independent hierarchical representations from high- to low-levels of abstractions. The model starts with learning the most abstract representation, and then progressively grow the network architecture to introd…
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementa…
University of California, San Diego（加州大学圣地亚哥分校）；SRI International（SRI国际）
Neural Ordinary Differential Equations (NODEs) have proven to be a powerful modeling tool for approximating (interpolation) and forecasting (extrapolation) irregularly sampled time series data. However, their performance degrades substantially when applied to real-world data, especially long-term data with complex behaviors (e.g., long-term trend across years, mid-term seasonality across months, and short-term local variation across days). To address the modeling of such complex data with different behaviors at different frequencies (time spans), we propose a novel progressive learning paradig…
Columbia University（哥伦比亚大学）；Stanford University（斯坦福大学）
Generative adversarial networks, which can generate metasurfaces based on a training set of high performance device layouts, have the potential to significantly reduce the computational cost of the metasurface design process. However, basic GAN architectures are unable to fully capture the detailed features of topologically complex metasurfaces, and generated devices therefore require additional computationally-expensive design refinement. In this Letter, we show that GANs can better learn spatially fine features from high-resolution training data by progressively growing its network architect…
Monash University Malaysia（马来西亚莫纳什大学）；The University of Oklahoma（俄克拉荷马大学）
Lung cancer classification in screening computed tomography (CT) scans is one of the most crucial tasks for early detection of this disease. Many lives can be saved if we are able to accurately classify malignant/cancerous lung nodules. Consequently, several deep learning based models have been proposed recently to classify lung nodules as malignant or benign. Nevertheless, the large variation in the size and heterogeneous appearance of the nodules makes this task an extremely challenging one. We propose a new Progressive Growing Channel Attentive Non-Local (ProCAN) network for lung nodule cla…
Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers
KTH Royal Institute of Technology（皇家理工学院）；Helmholtz AI（亥姆霍兹人工智能研究所）；Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Google（谷歌）；Digital Futures（数字未来）
University of Oxford（牛津大学）；Facebook AI Research（脸书人工智能研究院）
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent may set an internal curriculum by initially restricting its action space. Our approach uses off-policy reinforcement learning to estimate optimal value functions for multiple action spaces simultaneously and efficiently transfers data, value estimates, and state representations f…
In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process. Here we propose a new hypernetwork approach to grow artificial neural networks based on neural cellular automata (NCA). Inspired by self-organising systems and information-theoretic approaches to developmental biology, we show that our HyperNCA method can grow neural networks capable of solving common reinforcement learning tasks. Finally, we explore how the same approach can be used to build developmental metamorphosis networks capable of transforming their w…
Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation
School of Computation, Information and Technology, Technical University Munich（技术大学慕尼黑计算、信息与技术学院）；Department of Radiation Oncology, TUM School of Medicine, TUM University Hospital rechts der Isar, Technical University of Munich（肿瘤放射治疗科，TUM医学院，TUM大学医院rechts der Isar，技术大学慕尼黑）；Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich（生物医学影像中的机器学习研究所，海德堡慕尼黑）；Institute of Radiation Medicine, Helmholtz Center Munich（放射医学研究所，海德堡慕尼黑）；Munich Center of Machine Learning (MCML)（慕尼黑机器学习中心）；School of Biomedical Engineering and Imaging Sciences, King’s College London（生物医学工程与成像科学学院，伦敦国王学院）；Departament de Matemàtiques i Informàtica, Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM), Universitat de Barcelona（数学与计算机科学系，巴塞罗那人工智能在医学实验室（BCN-AIM），巴塞罗那大学）
Ultrasound (US) imaging is widely used for anatomical structure inspection in clinical diagnosis. The training of new sonographers and deep learning based algorithms for US image analysis usually requires a large amount of data. However, obtaining and labeling large-scale US imaging data are not easy tasks, especially for diseases with low incidence. Realistic US image synthesis can alleviate this problem to a great extent. In this paper, we propose a generative adversarial network (GAN) based image synthesis framework. Our main contributions include: 1) we present the first work that can synt…
Recent work introduced progressive network growing as a promising way to ease the training for large GANs, but the model design and architecture-growing strategy still remain under-explored and needs manual design for different image data. In this paper, we propose a method to dynamically grow a GAN during training, optimizing the network architecture and its parameters together with automation. The method embeds architecture search techniques as an interleaving step with gradient-based training to periodically seek the optimal architecture-growing strategy for the generator and discriminator.…
We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a functional steepest descent idea, we derive a simple criterion for deciding the best subset of neurons to split and a splitting gradient for optimally updating the off-springs. Theoretically, our splitting strategy is a second-order functional steepest descent for escaping saddle points in an $\infty$-Wasserstein metric space, on which the standard parametric gradient descent is a first-order steepest descent. Our met…
Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score, Context-FID, assessing the quality of synthetic time series sam…
We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best network within a functional neighborhood of the original network that includes a diverse set of candidate network structures. By using Taylor approximation, the optimal network structure in the neighborhood can be found with a greedy selection procedure. We show that firefly descent can flexibly grow networks both wider and dee…
We present a system comprising a hybridization of self-organized map (SOM) properties with spiking neural networks (SNNs) that retain many of the features of SOMs. Networks are trained in an unsupervised manner to learn a self-organized lattice of filters via excitatory-inhibitory interactions among populations of neurons. We develop and test various inhibition strategies, such as growing with inter-neuron distance and two distinct levels of inhibition. The quality of the unsupervised learning algorithm is evaluated using examples with known labels. Several biologically-inspired classification…
