Despite best efforts to explain the work intuitively, I found OpenAI’s writing on EPG a bit dense. I really wanted to understand it, but I couldn’t find any helpful third-party explanations about it. That’s why I decided to dig in to the paper and write this post: to provide an intuitive explanation of what’s going on with EPG.Read More
It’s Time for Data Science to Grow Up
Supervised learning has done wonders, but it’s fundamentally limited. The direct optimization of decision-making — most broadly, the field of reinforcement learning (RL)— is mature enough for the big leagues.Read More
Recent technological innovations have led to a new form of fake media - the “adversarial example”. The main difference between an adversarial example and previous forgery methods is that the adversarial example is designed to fool a computer instead of a human. This has far-reaching effects on machine learning-based systems ranging from content filters to self-driving cars. It is even possible for adversarial examples in the real world to fool physical models.Read More
Efficiency, productivity and collaboration are critical in scaling up machine learning. Being a machine learning practitioner means doing a significant amount of devops and systems integration. Enter Google Colaboratory. Its message is to "help disseminate machine learning education and research" using a Jupyter notebook environment that runs entirely in the cloud and integrated with your Google Drive.
One, around the topic of AI eliminating jobs and thoughts on how AI may change a security practitioner’s job, and two, about the possibility that AI could be misused or perhaps used by malicious actors with unintended negative consequences.Read More
Algorithmic trading has been around for decades and has, for the most part, enjoyed a fair amount of success in its varied forms.
Reinforcement learning (RL) on the other hand, is much more "hands off." In RL, an “agent” simply aims to maximize its reward in any given environment and tries to improve its decision making through trial and error as it experiences more examples.Read More
Though financial transactions are increasingly online and digital, much business is still conducted via analog means. Companies may prefer hand filled paper documents for their security, simplicity, or familiarity. However, accounting for and reconciling such transactions across invoices, receipts, bills, and contracts with multiple formats can be extremely challenging for high volume businesses.Read More
we propose an automated method for alerting on pallets or other trackable assets that are at high risk of loss. Underlying our approach is the assumption that items deviating significantly from an expected trajectory have an elevated risk of going missing.Read More
Factories could improve worker safety and reduce costs from machine, robot and worker error through incisive use of state-of-the-art deep learning techniques. Specifically, deep learning can be used to detect anomalies in video recordings of factory workers.Read More
Infosec can benefit from a machine learning approach however a significant amount of domain expertise is required in order to apply ML effectively.Read More
When creating a feature space for adversarial use cases like payment fraud, account takeover fraud and internal fraud, data scientists can rely on domain knowledge, intuition, personal experience and ultimately and if labeled data is available-variable selection.Read More