# Jeremy Jordan > Thoughts, ideas, and new things I've learned. Public Ghost content for AI and LLM tooling. Use `/llms-full.txt` for consolidated page and post context. Append `.md` to any post or page URL to get the content in Markdown (for example, `/example-post.md`). ## Pages - [About me.](https://www.jeremyjordan.me/about.md) - Hi👋 I'm Jeremy, welcome to my blog. I'm a machine learning engineer currently working on information retrieval and agent memory at Nvidia. I love the process of learning and building a better understanding of our world. I started this blog for two purposes: to write about what I'm learning in my o… - [Business Ideas](https://www.jeremyjordan.me/business-ideas.md) - [Data science and machine learning courses.](https://www.jeremyjordan.me/data-science-courses.md) - Below I've curated a list of online courses I've used to learn more about data science and machine learning. Udacity * Intro to Data Analysis [https://www.udacity.com/course/intro-to-data-analysis--ud170] * Machine Learning Engineer Nanodegree [https://www.udacity.com/course/machine-learning-engine… - [Data Science Topics](https://www.jeremyjordan.me/data-science.md) - This page contains most of the topics I've covered in a self-set curriculum as I study the field of data science (with a strong focus on machine learning). Bullets without a link are topics that I plan to get to, but will not post an article on in the immediate future. Links labeled "coming soon" a… - [My favorite talks.](https://www.jeremyjordan.me/my-favorite-talks.md) - Go Against the Grain with David Heinemeier Hansson The Education of a Reluctant Businessman with Yvon Chouinard (CEO of Patagonia) How To Speak by Patrick Winston Andrew Ng: Artificial Intelligence is the New Electricity Scott Young on the Best Way to Learn Anything Dan Ariely: On Dating & Relation… - [My favorite quotes.](https://www.jeremyjordan.me/quotes.md) - Here's a collection of some of my favorite quotes: Life "Do not fear mistakes. There are none." ― Miles Davis “Every man I meet is my superior in some way, and in that I learn from him.” ― Ralph Waldo Emerson “A master in the art of living draws no sharp distinction between his work and his play; h… - [Random software I love to use](https://www.jeremyjordan.me/random-software.md) - A collection of little software programs that I enjoy on my MacOS devices. BlackHole: Audio Loopback Driver This software allows you to easily record system audio. You can also configure your sound settings to output both to BlackHole (to record the audio) and your speakers (to hear what's being re… - [Saltzer and Schroeder's design principles](https://www.jeremyjordan.me/security-design.md) - 1. Economy of mechanism: Keep the design as simple and small as possible. 2. Fail-safe defaults: Base access decisions on permission rather than exclusion. 3. Complete mediation: Every access to every object must be checked for authority. 4. Open design: The design should not be secret. 5. Separati… - [Startup graveyard.](https://www.jeremyjordan.me/startup-graveyard.md) - I've worked on a lot of things. Many of them failed. Here's a list. * BoostOurTeam * A fundraising platform for high school sports teams. The neat idea here was that coaches could share key stats and highlights from each game and allow donors to pledge a certain amount of money according to a game… - [Talks and Presentations](https://www.jeremyjordan.me/talks.md) - Powering large-scale similarity search with deep learning Dec 2018 – Deep Learning RTP Meetup * Slides * Meetup Paper discussion on "mixup: Beyond Empirical Risk Minimization" Feb 2019 – Deep Learning RTP Meetup * Slides * Meetup 8 lessons learned building threat detection systems as an MLE Oct 202… - [Triathlons 🏊 🚴 🏃](https://www.jeremyjordan.me/triathlons.md) - I've been completing one sprint triathlon (750m swim, 20km bike, 5km run) every week since May 2023. I usually split the three activities into separate workouts; I'm mostly focused on ensuring that I hit my distance goals over the course of the week, and I'm not too strict on time splits for each a… ## Posts - [Exploring the age of continuous work.](https://www.jeremyjordan.me/continuous-work.md) - A few weeks ago, I was swimming laps after work, reflecting on my day. This eventually led to a spark of inspiration for a potential project, and I spent the rest of my workout mulling over this idea. As I biked home, I opened up my voice notes app and proceeded to do a verbal dump of my brainstorm… - [Training extremely large neural networks across thousands of GPUs.](https://www.jeremyjordan.me/distributed-training.md) - In this blog post, we'll discuss techniques such as data and model parallelism which allow us to distribute the model training process across a large cluster of machines. - [Understanding the Transformer architecture for neural networks](https://www.jeremyjordan.me/transformer-architecture.md) - The attention mechanism allows us to merge a variable-length sequence of vectors into a fixed-size context vector. What if we could use this mechanism to entirely replace recurrence for sequential modeling? This blog post covers the Transformer architecture which explores such an approach. - [Understanding the attention mechanism in sequence models](https://www.jeremyjordan.me/attention.md) - In this blog post, we'll discuss a key innovation in sequence-to-sequence model architectures: the attention mechanism. This architecture innovation dramatically improved model performance for sequence-to-sequence tasks such as machine translation and text summarization. Moreover, the success of th… - [Managing your machine learning infrastructure as code with Terraform](https://www.jeremyjordan.me/terraform.md) - Let's say you want to deploy a recommender system at your company. A typical architecture might include a set of inference servers to run your embedding and ranking models, an approximate nearest neighbor index to select a set of candidate items that match your query, a database to retrieve features - [Terraform configuration: quick reference](https://www.jeremyjordan.me/terraform-quick-reference.md) - This page contains a quick reference for writing Terraform configuration. - [A simple solution for monitoring ML systems.](https://www.jeremyjordan.me/ml-monitoring.md) - This blog post aims to provide a simple, open-source solution for monitoring ML systems. We'll discuss industry-standard monitoring tools and practices for software systems and how they can be adapted to monitor ML systems. - [Effective testing for machine learning systems.](https://www.jeremyjordan.me/testing-ml.md) - In this blog post, we'll cover what testing looks like for traditional software development, why testing machine learning systems can be different, and discuss some strategies for writing effective tests for machine learning systems. We'll also clarify the distinction between the closely related - [An introduction to Kubernetes.](https://www.jeremyjordan.me/kubernetes.md) - This blog post will provide an introduction to Kubernetes so that you can understand the motivation behind the tool, what it is, and how you can use it. In a follow-up post, I'll discuss how we can leverage Kubernetes to power data science workloads using more concrete (data science) examples. - [Building machine learning products: a problem well-defined is a problem half-solved.](https://www.jeremyjordan.me/ml-requirements.md) - Previously, I wrote about organizing machine learning projects where I presented the framework that I use for building and deploying models. However, that framework operates on the implicit assumption that you already know generally what your model should do. - [Introduction to recurrent neural networks.](https://www.jeremyjordan.me/introduction-to-recurrent-neural-networks.md) - In this post, I'll discuss a third type of neural networks, recurrent neural networks, for learning from sequential data. For some classes of data, the order in which we receive observations is important. As an example, consider the two following sentences: - [Scaling nearest neighbors search with approximate methods.](https://www.jeremyjordan.me/scaling-nearest-neighbors-search-with-approximate-methods.md) - In this blog post, I'll cover a couple of techniques used for approximate nearest neighbors search. This post will not cover approximate nearest neighbors methods exhaustively, but hopefully you'll be able to understand how people generally approach this problem and how to apply these techniques - [Organizing machine learning projects: project management guidelines.](https://www.jeremyjordan.me/ml-projects-guide.md) - The goal of this document is to provide a common framework for approaching machine learning projects that can be referenced by practitioners. If you build ML models, this post is for you. - [An overview of object detection: one-stage methods.](https://www.jeremyjordan.me/object-detection-one-stage.md) - In this post, I'll discuss an overview of deep learning techniques for object detection using convolutional neural networks. Object detection is useful for understanding what's in an image, describing both what is in an image and where those objects are found. - [Evaluating image segmentation models.](https://www.jeremyjordan.me/evaluating-image-segmentation-models.md) - When evaluating a standard machine learning model, we usually classify our predictions into four categories: true positives, false positives, true negatives, and false negatives. However, for the dense prediction task of image segmentation, it's not immediately clear what counts as a "true positive… - [An overview of semantic image segmentation.](https://www.jeremyjordan.me/semantic-segmentation.md) - In this post, I'll discuss how to use convolutional neural networks for the task of semantic image segmentation. Image segmentation is a computer vision task in which we label specific regions of an image according to what's being shown. - [Lessons learned from attempting to launch a startup.](https://www.jeremyjordan.me/mobius.md) - In Fall 2017, I made the decision to walk down the entrepreneurial path and dedicate a full-time effort towards launching a startup venture. I secured a healthy seed round of funding from a local angel investor and recruited three of my peers to join me in this effort. By Summer 2018, we decided to… - [Common architectures in convolutional neural networks.](https://www.jeremyjordan.me/convnet-architectures.md) - In this post, I'll discuss commonly used architectures for convolutional networks. As you'll see, almost all CNN architectures follow the same general design principles of successively applying convolutional layers to the input, periodically downsampling the spatial dimensions while increasing the… - [Variational autoencoders.](https://www.jeremyjordan.me/variational-autoencoders.md) - A variational autoencoder (VAE) provides a probabilistic manner for describing an observation in latent space. Thus, rather than building an encoder which outputs a single value to describe each latent state attribute, we'll formulate our encoder to describe a probability distribution - [Introduction to autoencoders.](https://www.jeremyjordan.me/autoencoders.md) - Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. Specifically, we'll design a neural network architecture such that we impose a bottleneck in the network which forces a compressed knowledge representation of the origin… - [Setting the learning rate of your neural network.](https://www.jeremyjordan.me/nn-learning-rate.md) - In previous posts, I've discussed how we can train neural networks using backpropagation with gradient descent. One of the key hyperparameters to set in order to train a neural network is the learning rate for gradient descent. - [Learning from imbalanced data.](https://www.jeremyjordan.me/imbalanced-data.md) - In this blog post, I'll discuss a number of considerations and techniques for dealing with imbalanced data when training a machine learning model. The blog post will rely heavily on a sklearn contributor package called imbalanced-learn to implement the discussed techniques. - [Normalizing your data (specifically, input and batch normalization).](https://www.jeremyjordan.me/batch-normalization.md) - In this post, I'll discuss considerations for normalizing your data - with a specific focus on neural networks. In order to understand the concepts discussed, it's important to have an understanding of gradient descent. - [New Year's Resolutions 2018](https://www.jeremyjordan.me/new-years-resolutions-2018.md) - After revisiting my 2017 resolutions and evaluating how well I adhered each resolution, I'd like to set forth my resolutions for the coming year. This year, I'll set more measurable goals so that I can more effectively evaluate my performance at the end of this year. - [Hyperparameter tuning for machine learning models.](https://www.jeremyjordan.me/hyperparameter-tuning.md) - When creating a machine learning model, you'll be presented with design choices as to how to define your model architecture. Often times, we don't immediately know what the optimal model architecture should be for a given model, and thus we'd like to be able to explore a range of possibilities. In… - [What the heck is blockchain?](https://www.jeremyjordan.me/blockchain-introduction.md) - Lately, I've been talking more and more about blockchain and its potential impact. As I've been learning more about the technology and sharing what I've learned with my friends, I've decided it would be useful to write an introductory post to the technology, paving the way for subsequent posts on h… - [Generalizing value functions for large state spaces.](https://www.jeremyjordan.me/rl-generalizing-value-functions.md) - Up until now, we've discussed the concept of a value function primarily as a lookup table. As our agent visits specific state-action pairs and continues to explore an environment, we update the value of that state-action pair independent of any other state-action pairs. When we'd like to know the v… - [Implementations of Monte Carlo and Temporal Difference learning.](https://www.jeremyjordan.me/rl-learning-implementations.md) - In the previous post [https://www.jeremyjordan.me/rl-learning-methods/], I discussed two different learning methods for reinforcement learning, Monte Carlo learning and temporal difference learning. I then provided a unifying view by considering $n$-step TD learning and establishing hybrid learning… - [Learning in a stochastic environment.](https://www.jeremyjordan.me/rl-learning-methods.md) - Previously, I discussed how we can use the Markov Decision Process [https://www.jeremyjordan.me/markov-decision-process] for planning in stochastic environments. For the process of planning, we already have an understanding of our environment via access to information given by the transfer function… - [Overview of reinforcement learning.](https://www.jeremyjordan.me/overview-of-reinforcement-learning.md) - Reinforcement learning is a method of learning where we teach the computer to perform some task by providing it with feedback as it performs actions. This is different from supervised learning in that we don't explicitly provide correct and incorrect examples of how the task should be completed, we… - [SQL for data analysis.](https://www.jeremyjordan.me/sql.md) - As a data scientist, you deal with a lot of data. For small datasets, maybe you just store this information in a CSV file and load it into Pandas [https://pandas.pydata.org/]. However, this isn't really a scalable solution and won't do too well if you're constantly updating and inserting new data.… - [Convolutional neural networks.](https://www.jeremyjordan.me/convolutional-neural-networks.md) - In my introductory post [https://www.jeremyjordan.me/neural-networks-representation/] on neural networks, I introduced the concept of a neural network that looked something like this. As it turns out, there are many different neural network architectures [http://www.asimovinstitute.org/neural-netwo… - [Deep neural networks: preventing overfitting.](https://www.jeremyjordan.me/deep-neural-networks-preventing-overfitting.md) - In previous posts, I've introduced the concept of neural networks [https://www.jeremyjordan.me/neural-networks-representation/] and discussed how we can train neural networks [https://www.jeremyjordan.me/neural-networks-training/]. For these posts, we examined neural networks that looked like this.… - [Planning in a stochastic environment.](https://www.jeremyjordan.me/markov-decision-process.md) - In this post, I'll be discussing how to calculate the best set of actions to complete a task whilst operating in a known environment, otherwise known as planning. For this scenario, we have complete knowledge over the system's dynamics including the reward of each state and a probabilistic model fo… - [Evaluating a machine learning model.](https://www.jeremyjordan.me/evaluating-a-machine-learning-model.md) - So you've built a machine learning model and trained it on some data... now what? In this post, I'll discuss how to evaluate your model, and practical advice for improving the model based on what we learn evaluating it. I'll answer questions like: * How well is my model doing? Is it a useful model?… - [Neural networks: training with backpropagation.](https://www.jeremyjordan.me/neural-networks-training.md) - In my first post on neural networks, I discussed a model representation for neural networks and how we can feed in inputs and calculate an output. We calculated this output, layer by layer, by combining the inputs from the previous layer with weights for each neuron-neuron connection. I mentioned t… - [Gradient descent.](https://www.jeremyjordan.me/gradient-descent.md) - Gradient descent is an optimization technique commonly used in training machine learning algorithms. Often when we're building a machine learning model, we'll develop a cost function which is capable of measuring how well our model is doing. This function will penalize any error our model makes (by… - [Principal components analysis (PCA).](https://www.jeremyjordan.me/principal-components-analysis.md) - Principal components analysis (PCA) is the most popular dimensionality reduction technique to date. It allows us to take an $n$-dimensional feature-space and reduce it to a $k$-dimensional feature-space while maintaining as much information from the original dataset as possible in the reduced datas… - [Neural networks: activation functions.](https://www.jeremyjordan.me/neural-networks-activation-functions.md) - Activation functions are used to determine the firing of neurons in a neural network. Given a linear combination of inputs and weights from the previous layer, the activation function controls how we'll pass that information on to the next layer. An ideal activation function is both nonlinear and d… - [Feature selection for a machine learning model.](https://www.jeremyjordan.me/feature-selection.md) - Feature selection can be an important part of the machine learning process as it has the ability to greatly improve the performance of our models. While it might seem intuitive to provide your model with all of the information you have with the thinking that the more data you provide the better it… - [Soft clustering with Gaussian mixed models (EM).](https://www.jeremyjordan.me/gaussian-mixed-models.md) - Sometimes when we're performing clustering on a dataset, there exist points which don't belong strongly to any given cluster. If we were to use something like k-means clustering [https://www.jeremyjordan.me/grouping-data-points-with-k-means-clustering/], we're forced to make a decision as to which… - [Neural networks: representation.](https://www.jeremyjordan.me/intro-to-neural-networks.md) - This post aims to discuss what a neural network is and how we represent it in a machine learning model. Subsequent posts will cover more advanced topics such as training and optimizing a model, but I've found it's helpful to first have a solid understanding of what it is we're actually building and… - [Support vector machines.](https://www.jeremyjordan.me/support-vector-machines.md) - Today we'll be talking about support vector machines (SVM); this classifier works well in complicated feature domains, albeit requiring clear separation between classes. SVMs don't work well with noisy data, and the algorithm scales roughly cubic $O(n^3)$ to input depending on your implementation (… - [Boosted trees.](https://www.jeremyjordan.me/boosted-trees.md) - Boosting is an iterative ensembling process where models are trained in a sequential order. These models are known as "weak learners" as they are simple prediction rules which only perform slightly better than a random guess (ie. slightly better than 50% accuracy). The general concept behind boosti… - [Random forests.](https://www.jeremyjordan.me/random-forests.md) - Decision trees [https://www.jeremyjordan.me/decision-trees/] are desirable in that they scale well to larger datasets, they are robust against irrelevant features, and it is very easy to visualize the rationalization between a decision tree's predictions. Further, decision trees have low bias as th… - [K-nearest neighbors.](https://www.jeremyjordan.me/k-nearest-neighbors.md) - Many machine learning techniques involve building a model that is capable of representing the data and then finding the optimal parameters for the model to minimize error. K-nearest neighbors, however, is an example of instance-based learning where we instead simply store the training data and use… - [Naive Bayes classification.](https://www.jeremyjordan.me/naive-bayes-classification.md) - Naive Bayes classification methods are quite simple (in terms of model complexity) and commonly used for tasks such as document classification and spam filtering. This algorithm works well for datasets with a large amount of features (ex. a body of text where every word is treated as a feature) but… - [Logistic regression.](https://www.jeremyjordan.me/logistic-regression.md) - The goal of logistic regression, as with any classifier, is to figure out some way to split the data to allow for an accurate prediction of a given observation's class using the information present in the features. (For instance, if we were examining the Iris flower dataset, our classifier would fi… - [Decision trees.](https://www.jeremyjordan.me/decision-trees.md) - Decision trees are one of the oldest and most widely-used machine learning models, due to the fact that they work well with noisy or missing data, can easily be ensembled to form more robust predictors, and are incredibly fast at runtime. Moreover, you can directly visual your model's learned logic… - [Decision trees for regression.](https://www.jeremyjordan.me/decision-trees-for-regression.md) - Before you read this post, go ahead and check out my post on decision trees for classification [https://www.jeremyjordan.me/decision-trees-for-classification/]. This post will be building on top of that, as you'll see that decision tree regressors are very similar to decision tree classifiers. Regr… - [Polynomial regression.](https://www.jeremyjordan.me/polynomial-regression.md) - Polynomial regression is very similar to linear regression, with a slight deviation in how we treat our feature-space. Confused? It'll make more sense in a minute, just bear with me. As a reminder, linear regression models are composed of a linear combination of inputs and weights. $${h _\theta }\l… - [Preparing data for a machine learning model.](https://www.jeremyjordan.me/preparing-data-for-a-machine-learning-model.md) - Before you're ready to feed a dataset into your machine learning model of choice, it's important to do some preprocessing so the data behaves nicely for our model. In an ideal world, you'll have a perfectly clean dataset with no errors or missing values present. In the real world, however, such dat… - [Machine learning overview.](https://www.jeremyjordan.me/machine-learning-overview.md) - Preface: this post is for the complete novice in the field of machine learning in an attempt to orient readers for my other posts on machine learning. This is a high-level view of machine learning. What the heck is machine learning? The whole concept of machine learning is figuring out ways in whic… - [Linear regression.](https://www.jeremyjordan.me/linear-regression.md) - Linear regression is used to predict an outcome given some input value(s). While machine learning classifiers use features to predict a discrete label for a given instance or example, machine learning regressors have the ability use features to predict a continuous outcome for a given instance or e… - [Decision trees for classification.](https://www.jeremyjordan.me/decision-trees-for-classification.md) - In this third post on supervised machine learning classifiers, I'll be talking about one of the oldest and most widely used techniques - decision trees. Decision trees work well with noisy or missing data and are incredibly fast at runtime. They're additionally nice because you can visualize the de… - [Spring Break in Silicon Valley](https://www.jeremyjordan.me/spring-break-in-silicon-valley.md) - This past week I was invited to spend my Spring Break in Silicon Valley meeting with startups founded or connected with NC State alumni. Here's a short description of each visit and my takeaways. General Remarks One of my favorite things about the Valley was a culture of people that were not afraid… - [On thinking critically and skepticism.](https://www.jeremyjordan.me/on-thinking-critically-and-skepticism.md) - It really clicked for me sophomore year of high school. I had gained an interest in eating healthy and was doing a lot of research online to figure out the optimal healthy lifestyle. Now, the area of health can be quite a confusing one seeing as almost every food in existence has an article talking… - [A guiding principle for life.](https://www.jeremyjordan.me/a-guiding-principle-for-life.md) - One day, when I was a freshman in college, I walked into my mentor's office and he clasped his hands together at his fingertips, moving both hands forward as one. He asked me, "what am I doing?" to which I replied, "I don't know." He proceeded to give me and hint and ask again, "This (motioning to… - [New Year's Resolutions 2017](https://www.jeremyjordan.me/new-years-resolutions-2017.md) - Be more intentional with my time. When reading On the Shortness of Life by Seneca, I came across the following passage: It is not that we have a short time to live, but that we waste a lot of it. Life is long enough, and a sufficiently generous amount has been given to us for the highest achievemen… - [Strategies for understanding a concept.](https://www.jeremyjordan.me/strategies-for-understanding-a-concept.md) - In my last post on learning (found here [https://www.jeremyjordan.me/on-learning-and-intrinsic-motivation/]), I presented a different way to think about the learning process. In this post, I'll focus mainly on the struggle phase and detail strategies for reaching your "a ha" moment. Think like a li… - [Grouping data points with k-means clustering.](https://www.jeremyjordan.me/grouping-data-points-with-k-means-clustering.md) - K-means clustering is a simple method for partitioning $n$ data points in $k$ groups, or clusters. Essentially, the process goes as follows: 1. Select $k$ centroids. These will be the center point for each segment. 2. Assign data points to nearest centroid. 3. Reassign centroid value to be the calc… - [On happiness in life.](https://www.jeremyjordan.me/on-happiness-in-life.md) - Life isn’t about happiness. Life is about feeling the full range of emotions. Life is about exploring the human capacity. Convenient happiness is a facade. Life presents its attributes in a dualistic nature. Pushing through pain allows us to experience bliss. Challenging ourselves, feeling weak and… - [Harvesting energy from vibrations for powering small electronics.](https://www.jeremyjordan.me/harvesting-energy-from-vibrations-for-powering-small-electronics.md) - Here's a paper I wrote examining piezoelectric vibration energy harvesters. Enjoy! Further reading (papers I didn't have time to read before turning this assignment in but would like to revisit): * Power transfer of piezoelectric generated energy [https://www.google.com/patents/US5703474] * Strateg… - [Atomic force microscopy for studying surface topology.](https://www.jeremyjordan.me/atomic-force-microscopy-for-studying-surface-topology.md) - Ever wonder what a surface looks like at the microscale? Atomic force microscopy is commonly used in materials science to visualize surface topology. While it is often considered to be quite slow, it is often a useful materials characterization technique. Image credit [http://staff.ustc.edu.cn/~bxl… - [Ductile to brittle transitions in materials.](https://www.jeremyjordan.me/ductile-to-brittle-transitions-in-materials.md) - Understanding of fracture behavior is useful in selecting materials for product designs, and it is incredibly valuable to know if a material will experience a ductile-brittle transition and what temperature this transition occurs. Knowledge of a material's ductile-brittle transition temperature can… - [On learning and intrinsic motivation.](https://www.jeremyjordan.me/on-learning-and-intrinsic-motivation.md) - During a tutoring session last week, I was working with one of my students and could tell that while she could solve most of her homework problems, she still didn't feel confident with the subject. I encouraged her to take some time to dissect the concepts and try to wrap her mind around them until… - [What is x-ray diffraction?](https://www.jeremyjordan.me/what-is-x-ray-diffraction.md) - X-ray diffraction is a common materials characterization technique that allows for identification of crystal orientations and interatomic spacing. X-rays are used for this because the wavelength is on the same length scale as interatomic spacing and lattice parameter values. What's going on? An x-r… - [How does scanning electron microscopy work?](https://www.jeremyjordan.me/scanning-electron-microscopy.md) - Ever wonder how we can see things so small, the human eye doesn't even know it exists? Today I'll be writing about how scanning electron microscopes allow us to see far beyond what traditional microscopes can provide. You see, optical microscopy (which uses visible light waves for imaging) only all… - [Identifying related bodies of text using TF-IDF vectorization.](https://www.jeremyjordan.me/identifying-related-bodies-of-text-using-tf-idf-vectorization.md) - Term frequency-inverse document frequency (TF-IDF) vectorization is a mouthful to say, but it's also a simple and convenient way to characterize bodies of text. Due to its simplicity, this method scales better than some other topic modeling techniques (latent dirichlet allocation, probabilistic lat… - [Rejection is not a setback, it's a redirection.](https://www.jeremyjordan.me/rejection-is-not-a-setback-its-a-redirection.md) - I decided to write this post after I found out that I was not selected to go on a trip sponsored and subsidized by my school. It was a really great opportunity to visit startups in New York that I was looking forward to, but there were only a limited number of seats available on the trip (understan… - [The lotus leaf: how nature makes water-repellent materials.](https://www.jeremyjordan.me/lotus-leaf-how-nature-makes-water-repellant-materials.md) - Ever wonder what makes a material water-repellent? Hydrophobic materials can be useful in a myriad of applications, basically anywhere where you don't want your things to get wet. To figure out how to engineer materials with better hydrophobic properties, scientists have turned to nature (specifica… - [Personal reflections on self-confidence.](https://www.jeremyjordan.me/how-to-gain-confidence-in-your-self.md) - This past Friday night I went home to cook dinner with my mom and spend some time with her as the school semester is winding down. After dinner, we were chatting and I told her that I see myself following the entrepreneurial path after graduating college. I said, "You know, somewhere along the way… - [Life is not a linear progression.](https://www.jeremyjordan.me/life-is-not-a-linear-progression.md) - Rather, it's a grand adventure. All too often during my college career, I find both my peers and myself under great pressure and stress trying to figure out what we want to do and how we want to live our lives. It's easy to find ourselves looking at life as if it is a linear progression, seeing as… - [My whiteboard stand-up desk.](https://www.jeremyjordan.me/my-whiteboard-stand-up-desk.md) - As a student who frequently spends long hours at my desk studying and doing homework, I often wish I could get up and move around or at least not be sitting all day. You've probably seen a number of articles detailing the negative health effects of sitting. So, this January I decided to treat mysel… ## Optional - [RSS Feed](https://www.jeremyjordan.me/rss/) - [Sitemap](https://www.jeremyjordan.me/sitemap.xml) - [Full content of pages and posts](https://www.jeremyjordan.me/llms-full.txt)