Amazon Textract
Amazon Textract is a service that automatically extracts text and data from scanned documents. Amazon Textract goes beyond simple optical character recognition (OCR) to also identify the contents of fields in forms and information stored in tables. Many companies today extract data from documents and forms through manual data entry that’s slow and expensive or through simple optical character recognition (OCR) software that is difficult to customize. Rules and workflows for each document and form often need to be hard-coded and updated with each change to the form or when dealing with multiple forms. If the form deviates from the rules, the output is often scrambled and unusable. Amazon Textract overcomes these challenges by using machine learning to instantly ‘read’ virtually any type of document to accurately extract text and data without the need for any manual effort or custom code. With Textract you can quickly automate document workflows, enabling you to process millions of document pages in hours. Once the information is captured, you can take action on it within your business applications to initiate next steps for a loan application or medical claims processing. Additionally, you can create smart search indexes, build automated approval workflows, and better maintain compliance with document archival rules by flagging data that may require redaction. …

ReLeQ
Despite numerous state-of-the-art applications of Deep Neural Networks (DNNs) in a wide range of real-world tasks, two major challenges hinder further advances in DNNs: hyperparameter optimization and lack of computing power. Recent efforts show that quantizing the weights and activations of DNN layers to lower bitwidths takes a significant step toward reducing memory bandwidth and power consumption by using limited computing resources. This paper builds upon the algorithmic insight that the bitwidth of operations in DNNs can be reduced without compromising their classification accuracy. While the use of eight-bit weights and activations during inference maintains the accuracy in most cases, lower bitwidths can achieve the same accuracy while utilizing less power. However, deep quantization (quantizing bitwidths below eight) while maintaining accuracy requires a great deal of trial-and-error, fine-tuning as well as re-training. By formulating quantization bitwidth as a hyperparameter in the optimization problem of selecting the bitwidth, we tackle this issue by leveraging a state-of-the-art policy gradient based Reinforcement Learning (RL) algorithm called Proximal Policy Optimization [10] (PPO), to efficiently explore a large design space of DNN quantization. The proposed technique also opens up the possibility of performing heterogeneous quantization of the network (e.g., quantizing each layer to different bitwidth) as the RL agent learns the sensitivity of each layer with respect to accuracy in order to perform quantization of the entire network. We evaluated our method on several neural networks including MNIST, CIFAR10, SVHN and the RL agent quantizes these networks to average bitwidths of 2.25, 5 and 4 respectively with less than 0.3% accuracy loss in all cases. …

Knapsack Problem
The knapsack problem or rucksack problem is a problem in combinatorial optimization: Given a set of items, each with a weight and a value, determine the number of each item to include in a collection so that the total weight is less than or equal to a given limit and the total value is as large as possible. It derives its name from the problem faced by someone who is constrained by a fixed-size knapsack and must fill it with the most valuable items. The problem often arises in resource allocation where there are financial constraints and is studied in fields such as combinatorics, computer science, complexity theory, cryptography, applied mathematics, and daily fantasy sports. The knapsack problem has been studied for more than a century, with early works dating as far back as 1897. The name ‘knapsack problem’ dates back to the early works of mathematician Tobias Dantzig (1884-1956), and refers to the commonplace problem of packing your most valuable or useful items without overloading your luggage. …

Residual Transfer Network (RTN)
The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain. We relax a shared-classifier assumption made by previous methods and assume that the source classifier and target classifier differ by a residual function. We enable classifier adaptation by plugging several layers into deep network to explicitly learn the residual function with reference to the target classifier. We fuse features of multiple layers with tensor product and embed them into reproducing kernel Hilbert spaces to match distributions for feature adaptation. The adaptation can be achieved in most feed-forward models by extending them with new residual layers and loss functions, which can be trained efficiently via back-propagation. Empirical evidence shows that the new approach outperforms state of the art methods on standard domain adaptation benchmarks. …