Published Mar 18, 2022

SDS 558: @JonKrohnLearns's Answers to Questions on Machine Learning

Join Jon Krohn as he unpacks his methodology for creating accessible machine learning curricula, explores deep learning's transformative role in HR through automation and job matching, and provides expert insights on selecting the best deep learning software, with a focus on Pytorch Lightning's efficiency.
Episode Highlights
Super Data Science: ML & AI Podcast with Jon Krohn logo

Popular Clips

Episode Highlights

  • NLP in HR

    Jon Krohn explores the application of deep learning in natural language processing (NLP) for human resources. At his day job at Nebula, he uses deep learning to understand resumes and job descriptions, automating HR workflows and helping people find suitable opportunities faster than traditional methods. This approach surpasses basic keyword searches, offering a more nuanced understanding of language.

    Well, at my day job at Nebula, we use deep learning to, quote unquote, understand natural language on resumes and in job descriptions in order to automate human resources workflows, thereby enabling talented people to land the right opportunities for them more rapidly than is otherwise possible.

    ---

    For those interested in a deeper dive into this topic, Jon provides additional resources, including a detailed webinar linked in the show notes 1 2.

       

    Software Tools

    Jon discusses the open-source software tools he prefers for deep learning applications, highlighting Pytorch Lightning as a lightweight wrapper for scaling models efficiently. He notes its appeal for training on large datasets and deploying models into production systems. Jon also compares Pytorch with Tensorflow and Keras, explaining that while Tensorflow is excellent for production deployments, Pytorch is more enjoyable and easier for model design.

    In a kind of brief summary, Tensorflow and Kerris are really great for production deployments. Still today, they have a lot more associated libraries for deploying deep learning models into different kinds of circumstances, like on servers, on mobile phones, into someone's web browser. Pytorch, on the other hand, is a lot more fun and easy to use.

    ---

    He suggests learning both Pytorch and Tensorflow, as mastering one makes it easier to learn the other 1 3.

       

    Practical Applications

    In his case studies, Jon illustrates the practical application of deep learning in natural language understanding. At Nebula, he leverages these technologies to enhance HR processes, demonstrating how deep learning can transform traditional workflows. This innovative use of NLP allows for a more sophisticated analysis of resumes and job descriptions, ultimately streamlining the hiring process.

    Finally, they asked me about a case study where I've used deep learning in practice. Well, at my day job at Nebula, we use deep learning to, quote unquote, understand natural language on resumes and in job descriptions in order to automate human resources workflows.

    ---

    Jon's work exemplifies the potential of deep learning to improve efficiency and accuracy in various applications 1.

Related Episodes