Aug
2,
2023
Using OpenAI’S CLIP Model on the iPhone: Semantic Search For Your Own Pictures
The iPhone Photos app supports text-based searches, but is quite limited. When I wanted to search for a photo of “my girlfriend taking a selfie at the beach,” it didn’t return any results, even though I was certain there was such a photo in my album. This prompted me to take action. Eventually, I integrated OpenAI’s CLIP model into the iPhone.
Jan
7,
2021
Real-time anomaly detection with Kafka and Isolation Forests
Anomalies - or outliers - are ubiquitous in data. Be it due to measurement errors of sensors, unexpected events in the environment or faulty behaviour of a machine. In many cases, it makes sense to detect such anomalies in real time in order to be able to react immediately. The data streaming platform Apache Kafka and the Python library scikit-learn provide us with the necessary tools for this.
Nov
19,
2019
How Deep Learning helps protect honeybees
Honey bee colony assessment is usually carried out by manually counting and classifying comb cells. Thiago da Silva Alves explains in this interview how deep learning can help to accomplish this time-consuming and error-prone task.
Sep
25,
2019
“Tricking an autonomous vehicle into not recognizing a stop sign is an evasion attack”
As machine learning technologies become more prevalent, the risk of attacks continues to rise. Which types of attacks on ML systems exist, how do they work, and which is the most dangerous? ML Conference speaker David Glavas answered our questions.
Jun
13,
2019
Reinforcement Learning: A gentle introduction and industrial application
Machine learning can be implemented in different ways, one of which is reinforcement learning. What exactly is reinforcement learning and how can we put it to use? Before the upcoming ML Conference, we spoke to Dr. Christian Hidber about the underlying ideas and challenges of reinforcement learning, and why it can be suited for application in an industrial setting.
May
6,
2019
Deep Learning with Java: Introduction to Deeplearning4j
Deep learning is now often considered to be the "holy grail" when it comes to developing intelligent systems. While fully automatic and autonomous machine learning is on the way, current solutions still require the understanding of a software developer or engineer. Deep learning, by contrast, is a sub-discipline of machine learning that promises deep-reaching learning success without human intervention and is oriented towards the function and operation of neural networks in the human brain.
Jun
6,
2018
Find the outlier: Detecting sales fraud with machine learning
We spoke to data expert Canburak Tümer about how machine learning is being used to detect fraud in sales transactions. Find out how ML technology is helping to keep this tricky job under control and what it looks for when crunching the data.