We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this transform preserves most of the signal information needed for classification while substantially reducing the spatial resolution and total signal size. We demonstrate that cascading a CNN with this representation performs on par with ImageNet classification models, commonly used in downstream tasks, such as the ResNet-50. We subsequently apply our trained hybrid ImageNet model as a base model on a detection system, which has typically larger image inputs. On Pascal VOC and COCO detection tasks we demonstrate improvements in the inference speed and training memory consumption compared to models trained directly on the input image.

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid model-based and model-free approach, LEArning and Planning with Semantics (LEAPS), consisting of a multi-target sub-policy that acts on visual inputs, and a Bayesian model over semantic structures. When placed in an unseen environment, the agent plans with the semantic model to make high-level decisions, proposes the next sub-target for the sub-policy to execute, and updates the semantic model based on new observations. We perform experiments in visual navigation tasks using House3D, a 3D environment that contains diverse human-designed indoor scenes with real-world objects. LEAPS outperforms strong baselines that do not explicitly plan using the semantic content. Deep reinforcement learning (DRL) has undoubtedly witnessed strong achievements in recent years (Silver et al., 2016; Mnih et al., 2015; Levine et al., 2016).

This document is designed to be a first-year graduate-level introduction to probabilistic programming. It not only provides a thorough background for anyone wishing to use a probabilistic programming system, but also introduces the techniques needed to design and build these systems. It is aimed at people who have an undergraduate-level understanding of either or, ideally, both probabilistic machine learning and programming languages. We start with a discussion of model-based reasoning and explain why conditioning as a foundational computation is central to the fields of probabilistic machine learning and artificial intelligence. We then introduce a simple first-order probabilistic programming language (PPL) whose programs define static-computation-graph, finite-variable-cardinality models. In the context of this restricted PPL we introduce fundamental inference algorithms and describe how they can be implemented in the context of models denoted by probabilistic programs. In the second part of this document, we introduce a higher-order probabilistic programming language, with a functionality analogous to that of established programming languages. This affords the opportunity to define models with dynamic computation graphs, at the cost of requiring inference methods that generate samples by repeatedly executing the program. Foundational inference algorithms for this kind of probabilistic programming language are explained in the context of an interface between program executions and an inference controller. This document closes with a chapter on advanced topics which we believe to be, at the time of writing, interesting directions for probabilistic programming research; directions that point towards a tight integration with deep neural network research and the development of systems for next-generation artificial intelligence applications.

We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous path on which the cross-entropy loss is non-increasing and gets arbitrarily close to zero. This implies that these networks have no sub-optimal strict local minima.

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning problematic. Recently, numerous methods have been proposed for continual learning, but due to differences in evaluation protocols it is difficult to directly compare their performance. To enable more meaningful comparisons, we identified three distinct continual learning scenarios based on whether task identity is known and, if it is not, whether it needs to be inferred. Performing the split and permuted MNIST task protocols according to each of these scenarios, we found that regularization-based approaches (e.g., elastic weight consolidation) failed when task identity needed to be inferred. In contrast, generative replay combined with distillation (i.e., using class probabilities as "soft targets") achieved superior performance in all three scenarios. In addition, we reduced the computational cost of generative replay by integrating the generative model into the main model by equipping it with generative feedback connections. This Replay-through-Feedback approach substantially shortened training time with no or negligible loss in performance. We believe this to be an important first step towards making the powerful technique of generative replay scalable to real-world continual learning applications.

Abstract--In this project, we combine AlphaGo algorithm with Curriculum Learning to crack the game of Gomoku. Modifications like Double Networks Mechanism and Winning Value Decay are implemented to solve the intrinsic asymmetry and short-sight of Gomoku. Our final AI AlphaGomoku, through two days' training on a single GPU, has reached humans' playing level. Free style Gomoku is an interesting strategy board game with quite simple rules: two players alternatively place black and white stones on a board with 15 by 15 grids and winner is the one who first reach a line of consecutive five or more stones of his or her color. It is popular among students since it can be played simply with a piece of paper and a pencil to kill the boring class time. It is also popular among computer scientists since Gomoku is a natural playground for many artificial intelligence algorithms.

Abstract--The automated wafer inspection and quality control is complex and time consuming task, which can be speed up using neuromorphic memristive architectures, as a separate inspection device or integrating directly into sensors. This paper presents the performance analysis and comparison of different neuromorphic architectures for patterned wafer quality inspection and classification. The application of nonvolatile memristive devices in these architectures ensures low power consumption, small on-chip area scalability. We demonstrate that Long-Short Term Memory (LSTM) outperforms other architectures for the same number of training iterations, and has relatively low on-chip area and power consumption. I. INTRODUCTION With the increase of density and complexity of semiconductor devices on the wafer, wafer surface inspection becomes increasingly complex, important, and time consuming task.

Financial forecasting is challenging and attractive in machine learning. There are many classic solutions, as well as many deep learning based methods, proposed to deal with it yielding encouraging performance. Stock time series forecasting is the most representative problem in financial forecasting. Due to the strong connections among stocks, the information valuable for forecasting is not only included in individual stocks, but also included in the stocks related to them. However, most previous works focus on one single stock, which easily ignore the valuable information in others. To leverage more information, in this paper, we propose a jointly forecasting approach to process multiple time series of related stocks simultaneously, using multi-task learning framework. Compared to the previous works, we use multiple networks to forecast multiple related stocks, using the shared and private information of them simultaneously through multi-task learning. Moreover, we propose an attention method learning an optimized weighted combination of shared and private information based on the idea of Capital Asset Pricing Model (CAPM) to help forecast. Experimental results on various data show improved forecasting performance over baseline methods.

Judging by the presentations at the 2018 Symposium on VLSI Technology, held in Honolulu this summer, the semiconductor industry has a challenge ahead of it: how to develop the special low-power hardware needed to support artificial intelligence-enabled networks. To meet society's needs for low-power-consumption machine learning (ML), "we do need to turn our attention to this new type of computing," said Naveen Verma, an associate professor of electrical engineering at Princeton University." While introducing intelligence into engineering systems has been what the semiconductor industry has been all about, Verma said machine learning represents a "quite distinct" inflection point. Accustomed as it is to fast-growing applications, machine learning is on a growth trajectory that Verma said is "unprecedented in our own industry" as ML algorithms have started to outperform human capabilities in a wide variety of fields. Faster GPUs driven by Moore's Law, and combining chips in packages by means of heterogenous computing, "won't be enough as we proceed into the future.

CA Technologies announced its participation in scientific research to discover how Internet of Things (IoT) applications can use a type of AI known as'deep learning' to imitate human decisions. The research will also explore how to prevent that AI-based decisions are not producing biased results. This three-year research project is named ALOHA (adaptive and secure deep learning on heterogeneous architectures). "The future of all technologies will include AI and deep learning in some way," said Otto Berkes, CTO, CA Technologies. "The expansion of complex, multi-layered IoT systems bring both security and software development challenges that AI and autonomous computing are uniquely positioned to address," he added.