AWS Deep Learning

Building Deep Learning Models for Digital Pathology Image Analysis

Keen Eye is an AI Platform company building deep learning models to guide better drug development and diagnostics. They support the pathologists to deliver accurate, standardized and undiscovered tissue insights in research and clinical studies. Keen Eye has migrated from an on-premise infrastructure to full AWS Cloud service leveraging EKS, S3, SageMaker and more.

Read More
Computer Vision

Building an Object Detection Model with the ML.NET Model Builder

In this video, Jon Wood shows us how to use the VoTT (Visual Object Tagging Tool) to generate data and use it in Model Builder to get an object detection model.

Read More

Jay McClelland: Neural Networks and the Emergence of Cognition | Lex Fridman Podcast #222

Jay McClelland, a cognitive scientist at Stanford, sits down for an amazing conversation with Lex Fridman. OUTLINE: 0:00 – Introduction 0:43 – Beauty in neural networks 5:02 – Darwin and evolution 10:47 – The origin of intelligence 17:29 – Explorations in cognition 23:33 – Learning representations by back-propagating errors 29:58 – Dave Rumelhart and cognitive […]

Read More
AI Research

Three Explorations on Pre-Training: an Analysis, an Approach, and an Architecture

In this talk from Xinlei Chen, Facebook AI Research, covers three of their recent explorations on pre-training. First is an analysis on object/attribute detection pre-training, which produces bottom-attention features extensively used in vision and language research. The main finding is that plain grid features can work equally well without object proposals, while being significantly faster. […]

Read More
Natural Language Processing

Ramping up your custom NLP tasks with Verseagility

On this episode of the AI Show, Timm Walz joins Seth to talk about how ramping up your custom NLP tasks with Verseagility  will benefit your data science workflow. He’ll demonstrate how to use the toolkit in combination with Azure Machine Learning.

Read More
Computer Vision Robotics

Visual Recognition beyond Appearances, and its Robotic Applications

The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance. Yezhou Yang, among others, recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk will present the speaker’s efforts over the last decade. […]

Read More
Computer Vision Natural Language Processing Research

Tightly Connecting Vision and Language

Remarkable progress has been made at the intersection of vision and language. While showing great promise, current vision and language models may only weakly “connect” the two modalities and often fail in the wild. In this talk, Goggle’s Soravit Changpinyo will present recent efforts aiming to bridge this gap along two dimensions: informativeness and controllability. […]

Read More
Databricks Machine Learning

Scaling AutoML-Driven Anomaly Detection with Luminaire

Zillow has built an orchestration framework around Luminaire, our open-source python library for hands-off time-series Anomaly Detection. Luminaire provides a suite of models and built-in AutoML capabilities which they process with Spark for distributed training and scoring of thousands of metrics. In this talk, learn the architecture of this framework and performance of the Luminaire […]

Read More
Computer Vision Python

Advanced Computer Vision with Python

Learn advanced computer vision using Python in this full (and free!) course. Learn state of the art computer vision techniques by building five projects with libraries such as OpenCV and Mediapipe. If you are a beginner, don’t be afraid of the term advance. Even though the concepts are advanced, they are not difficult to follow. […]

Read More