How to build your own Chat GPT-powered application LLMs (large-language models) have gone mainstream. Even the teachers at the school where my wife works are extoling their virtues. How do you build an application with them? That's the question I've been trying to answer over the past week. Here's what I'
Learn how to code Neural Networks from scratch with one of the greats Andrej Karpathy was director of artificial intelligence at Tesla, and is a founder of the research group OpenAI. Relatively few people know that he quite recently started a YouTube Channel, which is filled with interesting and important topics. Today, I'd like to highlight this video: What is it?
Reinforcement Learning - A Gentle Introduction Reinforcement learning is what I thought machine learning would be when I first heard about it. I remember reading Kasparov's book about his chess matches against Deep Blue, imagining all the clever algorithms they must have employed to create it. When I chose machine learning as a career
Machine learning Use deep learning to create embeddings for categorical variables Let's begin with the problem. Suppose we have some tabular data. This data might fit nicely in a spreadsheet or pandas dataframe. Now suppose one of the columns is categorical. This means it's value is one of a fixed number. For example, it could be '
Machine learning What are recurrent neural networks and how can you use them Recurrent neural networks (RNNs) are helpful for specific time-series problems. A time series problem is one where the x-axis is time, and the y-axis is something you want to measure. A typical time-series problem might be 'guess the next value'. Another might be 'classify this time series&
Data Engineering Data scientists should build reproducible pipelines Most ML courses/blogs/articles/tutorials etc, describe an ML project as consisting of (something like) the following steps: 1. Extract data 2. Explore data 3. Clean data 4. Engineer features 5. Train model 6. Validate model 7. Release model Steps 4-6 are repeated until the model is 'good
Machine learning A gentle introduction to neural networks I will continue my posts on machine-learning techniques by going 'under the hood' and describing how neural networks work. The target audience is people who want a high(ish)-level understanding of how neural networks operate. Not to the level of mathematics or code. But enough to have
Machine learning What are generative adversarial networks, and how can you use them? Suppose you want to create a picture that looks like a Picasso painting. How would you do it? Well, you could spend 10,000 hours training yourself. Or, you could spend much less time training a computer to do it. But how would I train a computer to do it?
Machine learning What are Autoencoders, and how can I use them? My first reaction to learning about autoencoders was, that's so cool. In this article, I want to describe from a high(ish) level what auto-encoders are, how they work, and how you can use them. Hopefully, you'll feel the same way I do by the end.
Product Management 12 principles of leadership in product management I didn't know what leadership was until I got my first job as a product manager. Before that point, I'd only ever led a team of two; then, I was in charge of a team of fifteen. I needed to learn how to lead, and I
Product Management What is a data product manager? When I first read the term data product manager on Udacity (a training website), my interest was instantly piqued. I have a background in data science and product management. What is this strange hybrid? I asked myself. Can knowing about it help my career? I began researching. The answer, it