Over the last few weeks we've been working on applying Deep Learning algorithms for a new VentureRadar feature we're adding in the coming weeks. This piqued my interest in finding out more about the startups leading the way in developing and applying Deep Learning, so I decided to pick out the eighteen highest ranked companies in this emerging field from the VentureRadar database, and take a closer look at them. You can also search VentureRadar for "Deep Learning" to find out about more companies in this exciting area. You can find out more about each company in the profiles below. Enlitic uses deep learning and image analysis to help doctors make diagnoses and spot abnormalities in medical images.

Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly exploit structured data and temporal information through the use of a neural network model. To the best of our knowledge, this task has not been addressed using these kind of architectures. For this reason, we propose two novel approaches, which combine Long Short-Term Memory networks and Graph Convolutional Networks to learn long short-term dependencies together with graph structure. The quality of our methods is confirmed by the promising results achieved.

In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. We then use a subset of the unlabeled data to fine tune the embeddings using distant supervision. The final CNNs and LSTMs are trained on the SemEval-2017 Twitter dataset where the embeddings are fined tuned again. To boost performances we ensemble several CNNs and LSTMs together. Our approach achieved first rank on all of the five English subtasks amongst 40 teams. 1 Introduction Determining the sentiment polarity of tweets has become a landmark homework exercise in natural language processing (NLP) and data science classes.

Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss, which reduces to the log loss in the typical case when there is a single correct response label. While this loss is insensitive to the identity of the assigned class in the case of misclassification, in practice it is often the case that some errors may be more detrimental than others. Here we present the bilinear-loss (and related log-bilinear-loss) which differentially penalizes the different wrong assignments of the model. We thoroughly test this method using standard models and benchmark image datasets. As one application, we show the ability of this method to better contain error within the correct super-class, in the hierarchically labeled CIFAR100 dataset, without affecting the overall performance of the classifier.

For effective treatment of Alzheimer disease (AD), it is important to identify subjects who are most likely to exhibit rapid cognitive decline. Herein, we developed a novel framework based on a deep convolutional neural network which can predict future cognitive decline in mild cognitive impairment (MCI) patients using flurodeoxyglucose and florbetapir positron emission tomography (PET). The architecture of the network only relies on baseline PET studies of AD and normal subjects as the training dataset. Feature extraction and complicated image preprocessing including nonlinear warping are unnecessary for our approach. Accuracy of prediction (84.2%) for conversion to AD in MCI patients outperformed conventional feature-based quantification approaches. ROC analyses revealed that performance of CNN-based approach was significantly higher than that of the conventional quantification methods (p < 0.05). Output scores of the network were strongly correlated with the longitudinal change in cognitive measurements. These results show the feasibility of deep learning as a tool for predicting disease outcome using brain images.

Speech detection (SD) greatly improves the separation of speech sources from background interferes [1]. Nowadays, SD techniques attract intense attentions in a general speech processing framework, including automatic speech recognition (ASR) [2], speech enhancement [3] and speech coding [1]. Recently, deep neural network (DNN) based 1D SD algorithms show great advantages over conventional voice activity detectors [4], [5]. The obvious benefits of such approaches lie on their easy integration into ASR, robust performance, and feature fusion capability. Zhang and Wu [4] introduced deep belief network and used stacked Bernoulli-Bernoulli restricted Boltzmann machines (RBMs) to conduct the 1D SD. The idea that incorporating temporal context correlation to strengthen the dynamical detection is widely used in network structure design [6], [7]. Other DNN based 1D SD strategies might either focus on improving the front-end acoustic feature inputs (e.g., acoustic models and statistical models) [8], [9], or exploiting the supervised network structure in terms of sample training [10]. These DNN based approaches rely on comprehensive network training, and then are applied to binarily label the speech activities in the time domain. However, 1D SD methods integrate frequency features, and cannot reveal information in the joint time-frequency domain, which are generally more expressive on speech activities, compared with the binary values in 1D SD approaches.

At its F8 developer conference in San Jose today, Facebook is announcing the launch of Caffe2, a new open source framework for deep learning, a trendy type of artificial intelligence (AI). Deep learning generally involves training artificial neural networks on lots of data, like photos, and then getting them to make inferences about new data. Today's announcement builds on Facebook's contributions to the Torch open source deep learning framework and more recently the PyTorch framework that the Facebook Artificial Intelligence Research (FAIR) group conceived. And last year Facebook talked about a system called Caffe2go. "PyTorch is great for research, experimentation and trying out exotic neural networks, while Caffe2 is headed towards supporting more industrial-strength applications with a heavy focus on mobile," Facebook AI Platform engineering lead Yangqing Jia wrote in a comment on Hacker News. "This is not to say that PyTorch doesn't do mobile or doesn't scale or that you can't use Caffe2 with some awesome new paradigm of neural network, we're just highlighting some of the current characteristics and directions for these two projects.

This is our ongoing PyTorch implementation for both unpaired and paired image-to-image translation. The code was written by Jun-Yan Zhu and Taesung Park. Check out the original CycleGAN Torch and pix2pix Torch code if you would like to reproduce the exact same results as in the papers. More example scripts can be found at scripts directory. To train a model on your own datasets, you need to create a data folder with two subdirectories trainA and trainB that contain images from domain A and B. You can test your model on your training set by setting phase'train' in test.lua.

It seems like artificial intelligence is everywhere. No longer the stuff of Ridley Scott and Stanley Kubrick flicks, AI has rapidly wormed its way into everyday news coverage and real-world business conversations. Since last April alone, the amount of published articles, blog posts and multimedia content featuring the words "AI" or "Artificial Intelligence" has more than doubled, according to Factiva. Talk of AI often centers around life-altering technological advancements such as driverless vehicles or genomic medicine. But the ad and marketing tech industry, always willing to capitalize on a trend, has joined in with a flood of new digital ad and marketing platforms and services branded as AI-fueled technologies.

"Drawing on your phone or computer can be slow and difficult -- so we created AutoDraw, a new web-based tool that pairs machine learning with drawings created by talented artists to help you draw," wrote Google Creative Lab's "creative technologist," Dan Motzenbecker, earlier this week. AutoDraw is one of Google's artificial intelligence (AI) experiments, working across platforms to let anyone, irrespective of their artistic flair, create something super quick with little more than a scribble. It guesses what you're trying to draw, then lets you pick from a list of previously created pictures. No worries!" is the general idea here. First up, AutoDraw is a super fun tool that gets increasingly addictive -- that much is clear. But what's also clear is that the tool is more a display of AI smarts than it is a tool to improve your artwork, because it would be just as easy to embody the exact same functionality within a text-based search engine. I mean, why bother drawing a crap dolphin ...