Ben Dickson

Ben is a software engineer and the founder of TechTalks. He writes about technology, business and politics.




  • Why machine learning struggles with causality
    By , a software engineer and founder, TechTalks on April 8, 2021 in Causality, Inference, Machine Learning
    If there's one thing people know how to do, and that's guess what caused something else to happen. Usually these guesses are good, especially when making a visual observation of something in the physical world. AI continues to wrestle with such inference of causality, and fundamental challenges must be overcome before we can have "intuitive" machine learning.


  • Silver BlogDeep learning doesn’t need to be a black box
    By , a software engineer and founder, TechTalks on February 5, 2021 in Convolutional Neural Networks, Deep Learning, Explainability, Explainable AI, Image Recognition
    The cultural perception of AI is often suspect because of the described challenges in knowing why a deep neural network makes its predictions. So, researchers try to crack open this "black box" after a network is trained to correlate results with inputs. But, what if the goal of explainability could be designed into the network's architecture -- before the model is trained and without reducing its predictive power? Maybe the box could stay open from the beginning.


  • Machine learning adversarial attacks are a ticking time bomb
    By , a software engineer and founder, TechTalks on January 29, 2021 in Adversarial, Generative Adversarial Network, Machine Learning
    Software developers and cyber security experts have long fought the good fight against vulnerabilities in code to defend against hackers. A new, subtle approach to maliciously targeting machine learning models has been a recent hot topic in research, but its statistical nature makes it difficult to find and patch these so-called adversarial attacks. Such threats in the real-world are becoming imminent as the adoption of machine learning spreads, and a systematic defense must be implemented.


  • Doing the impossible? Machine learning with less than one example
    By , a software engineer and founder, TechTalks on November 9, 2020 in Algorithms, K-nearest neighbors, Machine Learning, Research
    Machine learning algorithms are notoriously known for needing data, a lot of data -- the more data the better. But, much research has gone into developing new methods that need fewer examples to train a model, such as "few-shot" or "one-shot" learning that require only a handful or a few as one example for effective learning. Now, this lower boundary on training examples is being taken to the next extreme.


By subscribing you accept KDnuggets Privacy Policy

By subscribing you accept KDnuggets Privacy Policy