Deep Learning Workshop

NOTE: THIS IS A PAID WORKSHOP

REGISTRATION DETAILS HERE: http://www.analyticscertificate.com/DeepLearning

Deep learning is a technique for automatically finding hierarchical patterns in large sets of data, and has been used to achieve breakthrough advances in computer vision, machine translation, speech recognition, game playing, robotics, and other applications in recent years. The recent progress and future potential of deep learning has led to immense interest and to its adoption by all large technology companies.

In this workshop, we’ll introduce deep learning and demonstrate how it can be used in the above areas, with a focus on practical applications. We will explain the technological and algorithmic advances that have made it possible, describe the tools you can use to get started, and talk about the challenges to deploying deep learning systems in production.

What you will learn:

In this workshop, you will learn the core techniques used in Deep Learning. Through examples in Keras, Tensorflow and Apache Spark,you will learn:

Basics of Neural NetworksCore Deep Learning Techniques including CNNs,RNNs, AutoEncodersLimitations and challenges of using DNNs.Fine tuning and considerations when working with Deep Neural NetworksDeep Learning and Apache SparkPractical Case studies with fully functional code

Day 1:

On day one, we will review the core techniques in Deep learning neural networks. Through examples we will understand the different deep learning techniques and frameworks

Introduction to deep neural networksHands on with Keras and TensorFlowStatistical techniques in Anomaly DetectionConvolutional neural networks for computer visionRecurrent neural networks for translation, sentiment detection, and other text applicationsCase study 1: Classifying images using fully connected neural networks and convolutional networksCase study 2: Monitoring network learning and status using ad-hoc plots and TensorBoardCase study 3: Comparing performance of GPU and CPU network trainingCase study 4: Using pre-trained models for identifying objects in photos.

Day 2:

On day two, we will discuss more advanced techniques in deep learning. We will also discuss best practices in scaling and using deep learning techniques including using Apache Spark with Deep learning.

· Deep neural nets for reinforcement learning--games, robots, and self-driving cars

Hands on: tuning parameters, initial values, optimizers, and other practical issuesRecurrent Neural Networks, AutoEncoders and Reinforcement LearningApache Spark and Deep LearningFrontiers of deep learning: what’s coming in the next few yearsCase study 5: Understanding the word2vec text embeddingCase study 6: Using recurrent neural networks to caption images.Case study 7: Using an auto-encoder to de-noise images.Case study 8: Using neural-network-based reinforcement learning to play breakout

Instructors

Victor Shnayder, PHD leads the Deep Learning practice at Quant University. He has taught machine learning at Harvard, and helped design and teach many other courses in computer science, including distributed systems, sensor networks, economics and computation, systems, and theory of computation. He loves education, and was an early engineer at online education startup edX, later becoming the product manager for analytics and research. His team helped partner institutions process detailed traces of student activity, and created edX Insights, a tool to help course teams understand and better support their students’ learning. Previously, he worked on crowdsourcing and computer vision for document processing at Virtual Solutions. He has PhD and MS degrees in computer science from Harvard University, and a BSE in computer science from Princeton University.

Sri Krishnamurthy,CFA, CAP is the founder of QuantUniversity.com, a data and quantitative analysis company and the creator of the Analytics Certificate program (www.analyticscertificate.com). He has more than 15 years experience in analytics, quantitative analysis, statistical modeling and software development and has worked at Citigroup, Endeca, Mathworks and with more than 50 customers in the financial services and energy industries.He has trained more than 1000 students in quantitative methods, analytics and big data in the industry and at Babson College,Northeastern University and Hult International Business school.

Sponsors

We thank IBM and Microsoft for sponsoring these workshops