Schedule: Deep Learning sessions: Artificial Intelligence & Machine Learning Conference: O'Reilly AI

9:00am - 5:00pm Monday, September 9 & Tuesday, September 10

Location: Market (Hilton)

Deep learning with TensorFlow

Robert Schroll (The Data Incubator)

Average rating:

(5.00, 2 ratings)

The TensorFlow library provides computational graphs with automatic parallelization across resources, ideal architecture for implementing neural networks. Robert Schroll walks you through TensorFlow's capabilities in Python from building machine learning algorithms piece by piece to using the Keras API provided by TensorFlow with several hands-on applications. Read more.

9:00am - 5:00pm Monday, September 9 & Tuesday, September 10

Location: 112

Deep learning with PyTorch

Rich Ott (The Pragmatic Institute)

Average rating:

(3.00, 1 rating)

PyTorch is a machine learning library for Python that allows you to build deep neural networks with great flexibility. Its easy-to-use API and seamless use of GPUs make it a sought-after tool for deep learning. Get the knowledge you need to build deep learning models using real-world datasets and PyTorch with Rich Ott. Read more.

9:00am - 5:00pm Monday, September 9 & Tuesday, September 10

Location: Santa Clara Room (Hilton)

Natural language processing with deep learning

Delip Rao (AI Foundation), Brian McMahan (Wells Fargo)

Average rating:

(4.50, 4 ratings)

Delip Rao and Brian McMahan explore natural language processing using a set of machine learning techniques known as deep learning. They walk you through neural network architectures and NLP tasks and teach you how to apply these architectures for those tasks. Read more.

9:00am–12:30pm Tuesday, September 10, 2019

Location: LL21 E/F

Using Keras to classify text with LSTMs and other ML techniques

Models and Methods

Lukas Biewald (Weights & Biases)

Average rating:

(4.25, 4 ratings)

Join Lukas Biewald to build and deploy long short-term memories (LSTMs), grated recurrent units (GRUs), and other text classification techniques using Keras and scikit-learn. Read more.

1:30pm–5:00pm Tuesday, September 10, 2019

Location: LL21 A/B

Deep learning at scale: Tools and solutions

Implementing AI, Models and Methods

Angela Wu (Determined AI), Sidney Wijngaarde (Determined AI), Shiyuan Zhu (Determined AI), Vishnu Mohan (Determined AI)

Average rating:

(4.67, 3 ratings)

Success with DL requires more than just TensorFlow or PyTorch. Angela Wu, Sidney Wijngaarde, Shiyuan Zhu, and Vishnu Mohan detail practical problems faced by practitioners and the software tools and techniques you'll need to address the problems, including data prep, GPU scheduling, hyperparameter tuning, distributed training, metrics management, deployment, mobile and edge optimization, and more. Read more.

11:05am–11:45am Wednesday, September 11, 2019

Location: Expo Hall 3

Uber’s deep learning applications in NLP and conversational AI

Implementing AI

Huaixiu Zheng (Uber)

Average rating:

(4.33, 3 ratings)

Uber applies natural language processing (NLP) and conversational AI in a number of business domains. Huaixiu Zheng details how Uber applies deep learning in the domain of NLP and conversational AI. You'll learn how Uber implements AI solutions in a real-world environment, as well as cutting-edge research in end-to-end dialogue systems. Read more.

11:05am–11:45am Wednesday, September 11, 2019

Location: LL21 E/F

AI and deep learning enable 4x faster scans and productivity gains for clinical radiology

AI Business Summit, Impact of AI on Business and Society

Enhao Gong (Subtle Medical), Greg Zaharchuk (Stanford University)

Average rating:

(4.00, 1 rating)

Enhao Gong and Greg Zaharchuk detail AI solutions, cleared by the FDA and powered by industry framework, that deliver 4x–10x faster MRI scans, 4x faster PET scans, and up to 10x dosage reduction. Clinical evaluation at hospitals such as Hoag Hospital, UCSF, and Stanford demonstrates the significant and immediate values of AI to improve the productivity of healthcare workflow. Read more.

11:05am–11:45am Wednesday, September 11, 2019

Location: LL21 C/D

Unlocking the next stage in computer vision with deep neural networks

Implementing AI

Josh Weisberg (Zillow Group)

Advances in AI and deep learning enable new technologies to mimic how the human brain interprets scenes, objects, and images, which has major implications for businesses that need to extract meaning from overwhelming quantities of unstructured data. Josh Weisberg walks you through how implementing computer vision based in deep neural networks allows machines to see images in an entirely new way. Read more.

11:05am–11:45am Wednesday, September 11, 2019

Location: 230 C

Scaling AI at Cerebras

Implementing AI

Urs Köster (Cerebras Systems)

Average rating:

(5.00, 1 rating)

Long training times are the single biggest factor slowing down innovation in deep learning. Today's common approach of scaling large workloads out over many small processors is inefficient and requires extensive model tuning. Urs Köster explains why with increasing model and dataset sizes, new ideas are needed to reduce training times. Read more.

11:55am–12:35pm Wednesday, September 11, 2019

Location: 230 C

Improving OCR quality of documents using generative adversarial networks

Implementing AI

Nagendra Shishodia (EXL), Solmaz Torabi (EXL), Chaithanya Manda (EXL)

Average rating:

(5.00, 1 rating)

Every NLP-based document-processing solution depends on converting documents or images to machine-readable text using an optical character recognition (OCR) solution, but accuracy is limited by the quality of the images. Nagendra Shishodia, Solmaz Torabi, and Chaithanya Manda examine how GANs can bring significant efficiencies by enhancing resolution and denoising scanned images. Read more.

1:45pm–2:25pm Wednesday, September 11, 2019

Location: LL21 C/D

Sequence to sequence modeling for time series forecasting

Models and Methods

Arun Kejariwal (Independent), Ira Cohen (Anodot)

Average rating:

(4.40, 5 ratings)

Sequence to sequence (S2S) modeling using neural networks is increasingly becoming mainstream. In particular, it's been leveraged for applications such as speech recognition, language translation, and question answering. Arun Kejariwal and Ira Cohen walk you through how S2S modeling can be leveraged for the aforementioned use cases, visualization, real-time anomaly detection, and forecasting. Read more.

1:45pm–2:25pm Wednesday, September 11, 2019

Location: 230 C

Generative models for fixing image defects

Implementing AI

Akhilesh Kumar (Adobe)

Photographic defects such as noise, exposure, and blur can ruin the perfect shot. Adobe has developed a solution based on GAN that can identify the defective region in images and fix it. Akhilesh Kumar explores how this solution, which can also be applied to fix videos, is better than traditional algorithms and means you won't have to spend hours manually editing the images. Read more.

2:35pm–3:15pm Wednesday, September 11, 2019

Location: 230 C

Long-term real-time network traffic flow prediction using LSTM recurrent neural network

Models and Methods

Wei Cai (Cox Communications)

Real-time traffic volume prediction is vital in proactive network management, and many forecasting models have been proposed to address this. However, most are unable to fully use the information in traffic data to generate efficient and accurate traffic predictions for a longer term. Wei Cai explores predicting multistep, real-time traffic volume using many-to-one LSTM and many-to-many LSTM. Read more.

4:00pm–4:40pm Wednesday, September 11, 2019

Location: 230 C

Machine learning for autonomous driving: Recent advances and future challenges

Models and Methods

Li Erran Li (Scale | Columbia University)

Tremendous progress has been made in applying machine learning to autonomous driving. Li Erran Li explores recent advances in applying machine learning to solving the perception, prediction, planning, and control problems of autonomous driving as well as some key research challenges. Read more.

4:00pm–4:40pm Wednesday, September 11, 2019

Location: LL21 C/D

Interpreting millions of patient stories with deep learned OCR and NLP

Models and Methods

Stacy Ashworth (SelectData), Alberto Andreotti (John Snow Labs)

Much business data still exists as challenging scanned or snapped documents. Stacy Ashworth and Alberto Andreotti explore a real-world case of reading, understanding, classifying, and acting on facts extracted from such image files using state-of-the-art, open source, deep learning-based optical character recognition (OCR), natural language processing (NLP), and forecasting libraries at scale. Read more.

4:50pm–5:30pm Wednesday, September 11, 2019

Location: 230 C

Named entity recognition at scale with deep learning

Models and Methods

Sijun He (Twitter), Ali Mollahosseini (Twitter)

Average rating:

(4.00, 1 rating)

Twitter is what’s happening in the world right now. To connect users with the best content, Twitter needs to build a deep understanding of its noisy and temporal text content. Sijun He and Ali Mollahosseini explore the named entity recognition (NER) system at Twitter and the challenges Twitter faces to build and scale a large-scale deep learning system to annotate 500 million tweets per day. Read more.

11:55am–12:35pm Thursday, September 12, 2019

Location: 230 A

Artificial and human intelligence in healthcare

Interacting with AI

Maithra Raghu (Cornell University | Google Brain)

Average rating:

(4.75, 4 ratings)

With the fundamental breakthroughs in artificial intelligence and the significant increase of digital health data, there's been enormous interest in AI for healthcare applications. Maithra Raghu examines how to more effectively develop AI algorithms for these settings and the novel prediction challenges and successes arising from the interaction of AI algorithms and human experts. Read more.

11:55am–12:35pm Thursday, September 12, 2019

Location: 230 C

Data distribution search: Deep reinforcement learning to improvise input datasets

Implementing AI

Vijay Gabale (Infilect)

Beyond computer games and neural architecture search, practical applications of deep reinforcement learning (DRL) to improve classical classification or detection tasks are few and far between. Vijay Gabale outlines a technique and some experiences of applying DRL on improving the distribution input datasets to achieve state-of-the-art performance, specifically on object-detection tasks. Read more.

1:45pm–2:25pm Thursday, September 12, 2019

Location: 230 A

Industrialized capsule networks for text analytics

Implementing AI

Vijay Srinivas Agneeswaran (Walmart Labs), Abhishek Kumar (Publicis Sapient)

Vijay Agneeswaran and Abhishek Kumar explore multilabel text classification problems, where multiple tags or categories have to be associated with a given text or documents. Multilabel text classification occurs in numerous real-world scenarios, for instance, in news categorization and bioinformatics (such as the gene classification problem). Read more.

2:35pm–3:15pm Thursday, September 12, 2019

Location: 230 A

Improving revenue cycle management with deep learning: A healthcare case study

Case Studies

Sanji Fernando (Optum)

Average rating:

(5.00, 1 rating)

Sanji Fernando explores his experience building, deploying, and operating a deep learning model that improves hospital revenue cycle management, including business alignment, data preparation, model development, model selection, deployment, and operations. Sanji also details key knowledge and opportunities for improvement with deep learning models in healthcare. Read more.

4:00pm–4:40pm Thursday, September 12, 2019

Location: 230 A

Using deep learning models to extract the most value from 360-degree images

Models and Methods

Shourabh Rawat (Zillow)

Average rating:

(4.00, 2 ratings)

Lately, 360-degree images have become ubiquitous in industries from real estate to travel. They enable an immersive experience that benefits consumers but creates a challenge for businesses to direct viewers to the most important parts of the scene. Shourabh Rawat walks you through how to identify and extract engaging static 2-D images using specific algorithms and deep learning methods. Read more.

4:00pm–4:40pm Thursday, September 12, 2019

Location: 230 C

Building autonomous network operation using deep learning and AI

Implementing AI

Jisheng Wang (Mist Systems)

Increased complexity and business demands continue to make enterprise network operation more challenging. Jisheng Wang outlines the architecture of the first autonomous network operation solution along with two examples of ML-driven automated actions. He also details some of his experiences and the lessons he learned applying ML, DL, and AI to the development of SaaS-based enterprise solutions. Read more.

4:50pm–5:30pm Thursday, September 12, 2019

Location: 230 A

Deep learning coming to the tire industry: Warehouse staffing with RNN-LSTMs and pricing optimizations with DNNs

Implementing AI

Alex (Tianchu) Liang (American Tire Distributors)

Average rating:

(4.00, 1 rating)

Deep learning has been a sweeping revolution in the world of AI and machine learning. But sometimes traditional industries can be left behind. Alex Liang details two solutions where deep learning is used: a warehouse staffing solution where LSTM RNNs are used for staffing level forecasting and a pricing recommendation solution where DNNs were used for data clustering and demand modeling. Read more.