MULTIVARIATE TIME SERIES FORECASTING USING STATISTICAL AND MACHINE LEARNING MODELS
This lecture discusses the formulation Vector Autoregressive (VAR) Models, one of the most important class of multivariate time series statistical models, and neural network-based techniques.
GRADIENT DESCENT, DEMYSTIFIED
Viewers will leave the talk with a better understanding of iterative optimization and a template of their own for implementing GD in Python, should they feel this would enrich their understanding.
RACIAL BIAS IN FACIAL RECOGNITION SOFTWARE
This talk will cover the basics of facial recognition and the importance of having diverse datasets when building out a model. We’ll explore racial bias in datasets using real world examples and cover a use case for developing an OpenFace model.
DATAFY ALL THE THINGS
This session empower you to curate & create your own data sets. You’ll learn how to parse unstructured text, harvest data from interesting websites and public APIs and about capturing and dealing with sensor data.
MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING FOR DETECTING FAKE NEWS
Through use cases and examples, we will discuss the different fake news detection approaches from feature extraction to model construction. We will focus on how to leverage NLP to characterize and extract discriminative features of fake news.
EFFECTIVE TRANSFER LEARNING FOR NLP
In this talk, we explore parameter and data efficient mechanisms for transfer learning on text, and show practical improvements on real-world tasks. We demo the use of Enso, a newly open-sourced library designed to simplify transfer learning.
Artificial Intelligence at the Edge - Jameson Toole - ODSC Meetup
Building Data Science Infrastructure at the City of San Diego
Find out what type of data has city has, how a city uses its data to improve the lives of its residents and more.
User Segmentation in the Real World - A Practical Guide for Data Analysts
Ruben Kogel of VSCO walks through a logical methodology in how data analysts can approach user segmentation.
The Magic of Dimensionality Reduction
Voted one of the best talks at ODSC Europe 2017. Dimensionality reduction is one of the most crucial tools in a data scientists’ toolbox, and modern tools can yield truly magical results.
Telling Stories with Data
Data visualisation offers a brilliant way of bringing the raw numbers to life. This tutorial will introduce an audience-centred approach to visualising data.
Using AI to Answer Questions
AI expert, Joel Grus on AI systems that have a deeper understanding of the world and can demonstrate understanding through questioning and answering.
The State of Conversational AI
This exceptional talk gives a technical overview & review of current state-of-the-art deep learning & NLP tactics for chatbots and conversational interfaces
Building an Object Detection Toolkit in Tensorflow
In this talk, we will discuss how state of the art object detection techniques work. Moreover, we will explore an implementation of an open source Python object detection toolkit based on TensorFlow
Interpreting Predictions from Complex Models
With large modern datasets the best accuracy is often achieved by complex models even experts struggle to interpret. Here, we present a unified framework for interpreting predictions, namely SHAP (SHapley Additive exPlanations)
Data science for the 99%
Many small companies such as start-ups may never have a data science team. Learn ways in which this neglected majority can benefit from data science.
Application of AI and Data Science in the Medical World
Learn how AI is having a profound impact in the medical world
Advancing large-scale neural network predictions
Use BigQuery for deep learning to "democratize enterprise data"
Artificial Intelligence in the Enterprise
Accomplished AI expert Ronald Bodkin explains why AI is so hot, details enterprise use cases, and given you insights on how to get started on your AI journey
Deep Learning using PyTorch
PyTorch is new deep learning framework that enables new-age A.I. research using dynamic computation graphs
Rapid Prototyping Data Products using R Shiny
Learn the benefits of rapid prototyping using the popular R Shiny platform
Dealing with Overfitting When Crowdsourcing Financial Alpha
Quantopian is attempting to change Fnancial services by allowing anybody to research and design trading strategies.
Machine Learning For Beginners
This excellent primer teaches you the difference between AI, machine learning, and deep learning and also the basics of essential models in all three.
Modern Approaches to Finance
Given the high volume of accurate historical data and the underlying quantitative nature of the industry, the financial sector is well suited for machine learning. Today data science has found many integral roles in the this financial ecosystem