deep learning models
deep learning models are based on artificial neural networks, specifically, Convolutional Neural Networks (CNN)s, although they can also include propositional formulas or latent variables organized layer-wise in deep generative models such as the nodes in deep belief networks and deep Boltzmann machines.
Learning deep structured models
Many problems in real-world applications involve predicting several random variables that are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such dependencies. The goal of this paper is to combine MRFs with deep learning
Prediction as a candidate for learning deep hierarchical models of data
Recent findings [HOT06] have made possible the learning of deep layered hierarchical representations of data mimicking the brains working. It is hoped that this paradigm will unlock some of the power of the brain and lead to advances towards true AI. In this thesis I
Deep hidden physics models : Deep learning of nonlinear partial differential equations
We put forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time. Specifically, we approximate the unknown solution as well as the nonlinear dynamics by two deep neural
Classification of diabetic retinopathy images by using deep learning models
Diabetes or more precisely Diabetes Mellitus (DM) is a metabolic disorder happens because of high blood sugar level in the body. Over the time, diabetes creates eye deficiency also called as Diabetic Retinopathy (DR) causes major loss of vision. The symptoms can
Automated feature selection and churn prediction using deep learning models
In this competitive world, mobile telecommunications market tends to reach a saturation state and faces a fierce competition. This situation forces the telecom companies to focus their attention on keeping the customers intact instead of building a large customer base
A New Pre-Training Method for Training Deep Learning Models with Application to Spoken Language Understanding.
We propose a simple and efficient approach for pre-training deep learning models with application to slot filling tasks in spoken language understanding. The proposed approach leverages unlabeled data to train the models and is generic enough to work with any deep
Learning the structure of deep sparse graphical models
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidden units. The Indian buffet process has been used as a nonparametric Bayesian prior on the
Deep learning models for EEG-based rapid serial visual presentation event classification
We consider deep learning (DL) for event classification using electroencephalogram (EEG) measurements of brain activities. We proposed HDNN or hierarchical deep neural network, and CNN4EEG, a new convolution neural network (CNN). Both DL models are designed to
Marine Animal Detection and Recognition with Advanced Deep Learning Models .
This paper summarizes SIATMMLABs contributions in SEACLEF-2017 task . We took part in three subtasks with advanced deep learning models . In Automatic Fish Identification and Species Recognition task, we exploited different frameworks to detect the proposal boxes of
Deep investment in financial markets using deep learning models
The aim of this paper is to layout deep investment techniques in financial markets using deep learning models . Financial prediction problems usually involve huge variety of data- sets with complex data interactions which makes it difficult to design an economic model
Using an ensemble of generalised linear and deep learning models in the smm4h 2017 medical concept normalisation task
This paper describes a medical concept normalisation system developed for the 2nd Social Media Mining for Health Applications Shared Task 3. The proposed system contains three main stages: lexical normalisation, word vectorisation and classification. The lexical
Interpreting deep learning models for ordinal problems.
Machine learning algorithms have evolved by exchanging simplicity and interpretability for accuracy, which prevents their adoption in critical tasks such as healthcare. Progress can be made by improving interpretability of complex models while preserving performance. This
Similarity-based Contrastive Divergence Methods for Energy-based Deep Learning Models .
Energy-based deep learning models like Restricted Boltzmann Machines are increasingly used for real-world applications. However, all these models inherently depend on the Contrastive Divergence (CD) method for training and maximization of log likelihood of
Automatic Image Annotation Using Convex Deep Learning Models .
Automatically assigning semantically relevant tags to an image is an important task in machine learning . Many algorithms have been proposed to annotate images based on features such as color, texture, and shape. Success of these algorithms is dependent on
Deep Learning Models for Passability Detection of Flooded Roads.
In this paper we study and compare several approaches to detect floods and evidence for passability of roads by conventional means in Twitter. We focus on tweets containing both visual information (a picture shared by the user) and metadata, a combination of text and
Using translated data to improve deep learning author profiling models
In this report on our participation in the PAN shared task on author profiling, we describe our attempt to identify the gender of authors using their posted tweets and images. The data of interest are tweets in the English, Spanish and Arabic languages as well as images
Neurally-guided procedural models : learning to guide procedural models with deep neural networks
We present a deep learning approach for speeding up constrained procedural modeling. Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models , but they require many samples to produce
Promoter analysis and prediction in the human genome using sequence-based deep learning models
Motivation: Computational identification of promoters is notoriously difficult as human genes often have unique promoter sequences that provide regulation of transcription and interaction with transcription initiation complex. While there are many attempts to develop
Stage-wise training: An improved feature learning strategy for deep models
Deep neural networks currently stand at the state of the art for many machine learning applications, yet there still remain limitations in the training of such networks because of their very high parameter dimensionality. In this paper we show that network training performance
FREE IEEE PAPER