Most retrieval-augmented generation systems today feel a bit stiff. You ask a question. You wait. You get an answer. It works, but it doesn’t “feel” like a conversation.

When I wrote Grokking GenAI: Multimodal Reasoning with Gemini last year, multimodality felt like a breakthrough. An AI that could read text, look at images, listen to audio, and even understand code already felt futuristic. But over the past year, something important has changed.

Neural Radiance Fields (NeRF) are one of those ideas that sound abstract until you actually build one. Then suddenly, everything clicks. In this article, we’ll train a NeRF end-to-end, starting from raw images and camera poses, all the way to rendering RGB images and depth maps. The goal here is to use a minimal dataset to understand how NeRF works in practice.

Imagine you’re trying to plan a trip to Hawaii. You’ve got a few pictures of beautiful beaches, a list of things you want to see, and a rough budget in mind. How do you pull it all together? You might browse travel blogs, compare prices, and even watch videos of the islands. You’re using different kinds of information – pictures, text, and video – to make sense of your trip.

Do you read a lot? No? Well, let’s say you’re at a library looking for information on a specific topic. Instead of just browsing through every book on the shelves, you ask the librarian for help.

How do we trust that AI is making good decisions? How do we affirm the decisions of our typical deep neural networks? How can AI explain itself?

Machine learning has become increasingly prevalent in many areas of our lives, from recommending products to us on shopping websites, to determining who gets hired for a job.

Sometime last year, I stumbled upon a paper while I was trying to come up with a really basic way to implement a budget and expenditure planner using an RL agent.

TensorFlow is one of the most widely and well known tools for machine learning and with its various features, it maintains its versatility to operate in different use cases.

Google Cloud AutoML is pretty cool, in that it allows developers to easily train custom machine learning models for vision, natural language, and translation without writing model code.

Continued from part one, where we’ve completed pre-processing (cleaning, formatting, etc) the dataset. Let’s now go ahead to build our TensorFlow model to help suggest near-perfect used car prices.

You’ve got a used car you’d like to sell. You know the acquired price, but how do you measure how much a fair sale price would be based on how much it has been used? Let’s build a TensorFlow model to help suggest near-perfect used car prices.

The idea of one-hot encoding labels in supervised learning isn’t really new. The need for encoding categorical data birthed out of a necessity for data science and machine learning algorithms to understand categorical data.

We showed in the last post what tensors are, what the ‘flow’ means, and how they are represented in TensorFlow. Here, we’ll do something much more exciting.

TensorFlow is a machine learning library used to implement deep learning algorithms in Python, and is very popular for being the most generally used machine learning framework by researchers and industry experts.

In this final and 4th Part of our brief look into Linear Algebra, we’ll talk about the Transpose and Inverse of matrices.

Here’s the Part 3 of our brief look into Linear Algebra, and we’ll learn about matrix-vector multiplication, matrix-matrix multiplication, as well as some essential matrix multiplication properties to note.

In this Part 2 of our brief look into Linear Algebra, we’ll learn about matrix addition and subtraction, as well as matrix-scalar multiplication.

The goal for “The Flow of Tensors” series is to allow us understand how to build machine learning apps using the popular TensorFlow library. But the journey of every traveller always has a beginning. And for this journey, our beginning is a small part of mathematics known as Linear Algebra.

For me, it usually is a drag writing about experiences, but being a GCI Mentor for TensorFlow is an experience I want to pin for keep and make timely reference to.