Schedule: Deep Learning models sessions

Delip Rao explores natural language processing with deep learning, walking you through neural network architectures and NLP tasks and teaching you how to apply these architectures for those tasks. Read more.

Buisnesses use forecasting to make better decisions and allocate resources more effectively. Recurrent neural networks (RNNs) have achieved a lot of success in text, speech, and video analysis but are less used for time series forecasting. Join Yijing Chen, Dmitry Pechyoni, Angus Taylor, and Vanja Paunic to learn how to apply RNNs to time series forecasting. Read more.

In recent years, there's been a quantum leap in the performance of AI, as deep learning made its mark in areas from speech recognition to machine translation and computer vision. However, as artificial intelligence becomes increasingly popular, data privacy issues also gain traction. Yishay Carmiel reviews these issues and explains how they impact the future of deep learning development. Read more.

Alan Mosca shows how any deep learning model can be improved and made more secure with the use of targeted ensemble methods and other similar techniques and demonstrates how to use these techniques in the Toupee deep learning framework to create production-ready models. Read more.

Imagine building a model whose training data is collected on edge devices such as cell phones or sensors. Each device collects data unlike any other, and the data cannot leave the device because of privacy concerns or unreliable network access. This challenging situation is known as federated learning. Ryan Micallef discusses the algorithmic solutions and the product opportunities. Read more.

Andrea Pasqua investigates the merits of using deep learning and other machine learning approaches in the area of forecasting and describes some of the machine learning approaches Uber uses to forecast time series of business relevance. Read more.

Bruno Fernandez-Ruiz details a unified network that jointly performs various mission-critical tasks in real time on a mobile environment, within the context of driving. Along the way, he outlines the challenges that emerge when training a single mobile network for multiple tasks, such as object detection, object attributes recognition, classification, and tracking. Read more.

Neural networks are particularly vulnerable to adversarial inputs. Carefully designed perturbations can lead a well-trained model to misbehave, raising new concerns about safety-critical and security-critical applications. Pin-Yu Chen offers an overview of CLEVER, a comprehensive robustness measure that can be used to assess the robustness of any neural network classifiers. Read more.

Gaurav Chakravorty explains how recommender systems can be utilized for investment management and details how AI and deep learning are used in trading today. Read more.

Vitaly Kuznetsov and Zelda Mariet compare sequence-to-sequence modeling to classical time series models and provide the first theoretical analysis of a framework that uses sequence-to-sequence models for time series forecasting. Read more.

The availability of large idea repositories (e.g., patents) could significantly accelerate innovation and discovery by providing people inspiration from solutions to analogous problems. Dafna Shahaf presents an algorithm that automatically discovers analogies in unstructured data and demonstrates how these analogies significantly increased people's likelihood of generating creative ideas. Read more.

The common perception of applying deep learning is that you take an open source or research model, train it on raw data, and deploy the result as a fully self-contained artifact. The reality is far more complex. Nick Pentreath shares lessons learned building a deep learning model exchange and discusses the future of standardized cross-framework deep learning model training and deployment. Read more.

While great strides have been made in perceptual AI (for example, in speech recognition), there's been relatively modest progress in reasoning AI—systems that can interact with us in natural ways and understand the objects in our environment. David Barber explains why general AI will be out of reach until we address how to endow machines with knowledge of our environment. Read more.

Even in the age of big data, labeled data is a scarce resource in many machine learning use cases. Florian Wilhelm evaluates generative adversarial networks (GANs) when used to extract information from vehicle registrations under a varying amount of labeled data, compares the performance with supervised learning techniques, and demonstrates a significant improvement when using unlabeled data. Read more.

Transfer learning allows data scientists to leverage insights from large labeled datasets. The general idea of transfer learning is to use knowledge learned from tasks for which a lot of labeled data is available in settings where only little labelled data is available. Lars Hulstaert explains what transfer learning is and demonstrates how it can boost your NLP or CV pipelines. Read more.

On his journey to the top spot at Kaggle, Marios Michailidis noticed that many of the things he does to perform competitively in data challenges could be automated. Marios shares lessons learned from his Kaggle experience and shows how you can achieve competitive performance in predictive modeling tasks automatically, using H2O.ai’s Driverless AI—an AI that creates AI. Read more.

Peter Cahill explains why Wavenet will be the next generation of recognition, synthesis, and voice-activity detection. Read more.

Dramatic progress has been made in computer vision. Deep neural networks (DNNs) trained on millions of images can recognize thousands of different objects, and they can be customized to new use cases. Vanja Paunic and Patrick Buehler outline simple methods and tools that enable users to easily and quickly adapt Microsoft's state-of-the-art DNNs for use in their own computer vision solutions. Read more.