Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

Deep learning

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.

The Nature of Statistical Learning Theory

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to ½ everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.

/pdf/generative-adversarial-nets-1ofhan3sbf.pdf

Generative Adversarial Nets

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition models when a speech recognizer does not have access to a speech recognition model for that domain of interest and when available domain-specific data is below a minimum desired threshold to create a new domain-specific speech recognition model. A system configured to practice the method identifies a speech recognition domain and combines a set of speech recognition models, each speech recognition model of the set of speech recognition models being from a respective speech recognition domain. The system receives an amount of data specific to the speech recognition domain, wherein the amount of data is less than a minimum threshold to create a new domain-specific model, and tunes the combined speech recognition model for the speech recognition domain based on the data.

System and method for rapid customization of speech recognition models

A system and method is provided for rapidly generating a new spoken dialog application. In one embodiment, a user experience person labels the transcribed data (e.g., 3000 utterances) using a set of interactive tools. The labeled data is then stored in a processed data database. During the labeling process, the user experience person not only groups utterances in various call type categories, but also flags (e.g., 100-200) specific utterances as positive and negative examples for use in an annotation guide. The labeled data in the processed data database can also be used to generate an initial natural language understanding (NLU) model.

System and method for automatic generation of a natural language understanding model

Presents a new image compression technique called "DjVu" that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color. With DjVu, any screen connected to the Internet can access and display images of scanned pages while faithfully reproducing the font, color, drawings, pictures and paper texture. A typical magazine page in color at 300 dpi can be compressed down to between 40 to 60 KBytes, approximately 5 to 10 times better than JPEG for a similar level of subjective quality. Black-and-white documents are typically 15 to 30 KBytes at 300 dpi, or 4 to 8 times better than CCITT-G4. A real-time, memory-efficient version of the decoder was implemented, and is available as a plug-in for popular Web browsers.

Browsing through high quality document images with DjVu

Several improvements in the Back-Propagation procedure are proposed to increase training speed, and we discuss their limitations with respect to generalization. performance. The error surface is modeled to avoid local minima and flat areas. The synaptic weights are updated as often as possible. Both the step size and the momentum are dynamically scaled to the largest possible values that do not result in overshooting. Training for the speaker-dependent recognition of the phonemes /b/, /d/ and /g/ has been reduced from 2 days to 1 minnte on an Alliant parallel computer, delivering the same 98.6% recognition performance. With a 55000-connection TDNN, the same algorithm needs 1 hour and 5000 training tokens to recognize the 18 Japanese consonants with 96.7% correct.

Fast back-propagation learning methods for large phonemic neural networks.

A method for identifying traffic to an application including the steps of monitoring communication traffic in a network, identifying data from communication traffic content, and constructing a model for mapping the communication traffic for an application derived from data identified from the communication traffic content is described. A related system and computer readable medium for performing the method is also described. The described method and system has utility in a wide array of networks including IP networks.

Patrick Haffner

Papers

System and method for rapid customization of speech recognition models

System and method for automatic generation of a natural language understanding model

Browsing through high quality document images with DjVu

Fast back-propagation learning methods for large phonemic neural networks.

Application signature based traffic classification