Cross Section and Deep Dive into TensorFlow.

Agenda:

5:30 - Doors open. Initiation of the new guild members.

5:45 - Networking & Pizza. Meet the members.
6:45 - Welcome. Members to share topics of interests for future meetings.
7:00 - Talk #1. Overview of Tensorflow by Stanley Bishop
7:30 - Q&A break.
7:45 - Talk #2. Learning to Diagnose with LSTM Recurrent Neural Networks by Dave Kale
8:15 - Talk #3. Machine Learning in Different Types of Businesses. How do we benefit from it? by Sanjay Prajapati

8:30 - Q&A break & wrap-up.

Talk #1: Overview of Tensorflow

• what TensorFlow is,

• what makes it unique from other options,

• the core API components of TensorFlow (TensorFlow Variables, placeholders, the Session, etc.)

Speaker: Sam Abrahams, Freelance Data Engineer

Talk #2: Learning to Diagnose with LSTM Recurrent Neural Networks.

Clinical medical data, especially in the intensive care unit (ICU), consist of multivariate time series of observations. For each patient visit (or episode), sensor data and lab test results are recorded in the patient's Electronic Health Record (EHR). While potentially containing a wealth of insights, the data is difficult to mine effectively, owing to varying length, irregular sampling and missing data. Recurrent Neural Networks (RNNs), particularly those using Long Short-Term Memory (LSTM) hidden units, are powerful and increasingly popular models for learning from sequence data. They effectively model varying length sequences and capture long range dependencies. We present the first study to empirically evaluate the ability of LSTMs to recognize patterns in multivariate time series of clinical measurements. Specifically, we consider multilabel classification of diagnoses, training a model to classify 128 diagnoses given 13 frequently but irregularly sampled clinical measurements. First, we establish the effectiveness of a simple LSTM network for modeling clinical data. Then we demonstrate a straightforward and effective training strategy in which we replicate targets at each sequence step. Trained only on raw time series, our models outperform several strong baselines, including a multilayer perceptron trained on hand-engineered features.

Speaker:

Dave Kale is a fourth year PhD student in Computer Science, Viterbi Dean's Doctoral Fellow, and Alfred E. Mann Innovation in Engineering Fellow at the University of Southern California. His research uses machine learning to extract insight from digital data in high impact domains, including but not limited to health care. He is advised by Prof. Greg Ver Steeg. Dave is also affiliated with the Laura P. and Leland K. Whittier Virtual Pediatric Intensive Care Unit (VPICU) at Children's Hospital, where he worked for three years as a data scientist. He help organize the annual Meaningful Use of Complex Medical Data (MUCMD) Symposium and is a co-founder of Podimetrics. He is a judge in the Qualcomm Tricorder XPRIZE Competition. Even further back, Dave completed his BS in Symbolic Systems and MS in Computer Science at Stanford University. Go Cardinal.

Talk #3: Machine Learning in Different Types of Businesses. How do we benefit from it?
● What is Machine learning

● Understanding of machine learning

● Why it is becoming important for us to explore into this field

● What are the impacts going to be in any business with the help of machine learning

● Benefits of ML in different industries.

Speaker: Sanjay Prajapati, President @ eBiz Intel Solutions LLC

Sanjay earned his Bachelor’s of Engineering in Computer Engineering in 2007 from India’s prestigious L.D. College of Engineering. He started his career working with payment gateway APIs, focusing on security in eCommerce platforms. Sanjay came to USA in 2008 where he completed a Masters in Computer Science and also gained his MBA from San Diego’s National University. Having more than 8 years of experience and education both in technical and business roles makes Sanjay’s work shine. Sanjay is currently working with Patch of Land and also he is a president of eBiz Intel Solutions LLC which focuses on providing businesses smarter solutions which can help businesses improve their weak area as well as put more focus on their stronger areas.