The Field Guide: a map of AI concepts | Farez Vadsaria

How to use it: open any term and its route shows every idea to understand first, basics first. Landmarks are the concepts the rest of the map leans on, which makes them good first stops.

Foundations

78 terms · 8 landmarks

Core ML ideas, classic algorithms, and the data they learn from.

Landmark · leads to 11 Supervised Learning Learning from examples paired with the correct answer, so a model can predict answers for new inputs it hasn't seen. Landmark · leads to 11 Training Data The examples a model learns its weights from, kept separate from the validation and test data used to check how well it generalizes. Landmark · leads to 10 Classification A supervised learning task where the model assigns each input to one of a fixed set of categories, such as spam or not spam. Landmark · leads to 10 Feature A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model. Landmark · leads to 7 Regression A supervised learning task where the model predicts continuous numerical values rather than discrete categories. Landmark · leads to 6 Machine Learning Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples. Landmark · leads to 6 Unsupervised Learning Learning from unlabeled data to discover hidden patterns, structures, or relationships without explicit target outputs. Landmark · leads to 0 Generalization A model's ability to perform well on new data it never saw during training, which is the whole point of learning from examples.

All 78 Foundations terms

Neural Networks

71 terms · 9 landmarks

Layers, activations, backprop: the building blocks of deep learning.

Landmark · leads to 35 Neural Network A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs. Landmark · leads to 14 Convolutional Neural Network A neural network that scans images with small learned filters, reusing the same weights at every position to build up from edges to whole objects. Landmark · leads to 8 Softmax A function that turns a list of scores (logits) into probabilities that are all positive and sum to 1; the standard output of classifiers and language models. Landmark · leads to 7 Recurrent Neural Network A neural network architecture with loops that allow information to persist, designed for sequential data like text and time series. Landmark · leads to 6 Activation Function A non-linear function applied to neuron outputs that introduces non-linearity, enabling networks to learn complex patterns. Landmark · leads to 5 Deep Learning A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data. Landmark · leads to 3 Parameter A number inside a model, a weight or a bias, that training adjusts to reduce the loss. Together, a model's parameters are everything it has learned. Landmark · leads to 2 Representation Learning Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand. Landmark · leads to 1 Dropout A regularization technique that randomly switches off units during training so the network can't lean on any one of them, which reduces overfitting.

All 71 Neural Networks terms

Training

80 terms · 11 landmarks

Losses, optimizers, regularization, and how models actually learn.

Landmark · leads to 17 Training The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error. Landmark · leads to 12 Gradient Descent An optimization method that repeatedly moves a model's parameters a small step in the direction that most reduces the loss. Landmark · leads to 12 Loss Function A function that scores how wrong a model's prediction is as a single number, which training then works to make as small as possible. Landmark · leads to 9 Overfitting When a model fits its training data too closely, noise included, so it scores well on examples it has seen and poorly on new ones. Landmark · leads to 7 Pre-training Training a model on a large dataset (often self-supervised) before fine-tuning on specific tasks, enabling transfer learning. Landmark · leads to 6 Fine-Tuning The process of further training a pre-trained model on a specific dataset to adapt it for a particular task or domain. Landmark · leads to 5 Backpropagation The algorithm for computing gradients of the loss with respect to network weights, enabling training through gradient descent. Landmark · leads to 4 Learning Rate The hyperparameter that sets how big a step gradient descent takes on each update; too high makes training unstable, too low makes it crawl. Landmark · leads to 3 Regularization Any change to training meant to make a model generalize better rather than fit its training data more closely, such as weight penalties, dropout or early stopping. Landmark · leads to 2 Hyperparameter A setting chosen before training, such as the learning rate or batch size, that controls how a model learns but isn't itself learned from the data. Landmark · leads to 2 Self-Supervised Learning Training on unlabeled data by making the data supply its own answers: hide or alter part of an input and have the model predict or match it.

All 80 Training terms

Evaluation

45 terms · 7 landmarks

Metrics, benchmarks, and knowing whether a model is any good.

Landmark · leads to 3 Recall The share of actual positives a model correctly identifies, TP / (TP + FN); also called sensitivity or the true positive rate. Landmark · leads to 2 False Positive A case the model labels positive that is actually negative, such as a legitimate email sent to spam. Statisticians call it a Type I error. Landmark · leads to 2 Precision Of everything a model flagged as positive, the fraction that really was positive: TP / (TP + FP). It answers "when the model says yes, how often is it right?" Landmark · leads to 2 Test Set Data locked away until the end of a project and used once to estimate how the finished model will perform on new, unseen examples. Landmark · leads to 2 Validation Set Data held back from training and used to choose hyperparameters and checkpoints, so those choices are judged on examples the model never fit. Landmark · leads to 1 Accuracy The share of predictions a classifier gets right. Simple and intuitive, but misleading when one class is much rarer than the others. Landmark · leads to 1 Intersection over Union A score from 0 to 1 for how well a predicted region matches the true one: the area they share divided by the area they cover together.

All 45 Evaluation terms

Language & LLMs

118 terms · 14 landmarks

Tokens, attention, transformers, prompting, and large language models.

Landmark · leads to 18 Large Language Model A neural network, almost always a transformer, trained on vast amounts of text to predict the next token, which lets it write, answer, summarize and follow instructions. Landmark · leads to 16 Embedding A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together. Landmark · leads to 11 Natural Language Processing The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots. Landmark · leads to 10 Transformer A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model. Landmark · leads to 8 Language Modeling Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models. Landmark · leads to 8 Tokenization Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it. Landmark · leads to 7 Attention Mechanism A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step. Landmark · leads to 7 Token The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary. Landmark · leads to 6 Self-Attention An attention step in which every token in a sequence looks at every token in that same sequence and builds a new representation from a weighted mix of them. Landmark · leads to 4 Prompt Engineering Designing a model's input (instructions, context, examples and output format) to get better results without changing the model itself. Landmark · leads to 2 Context Window The maximum number of tokens a language model can take into account at once, counting both the input it reads and the output it writes. Also called context length. Landmark · leads to 1 Hallucination When a language model produces fluent, confident output that is false or unsupported by its sources, such as invented facts, quotes or citations. Landmark · leads to 1 Retrieval-Augmented Generation Fetching relevant documents at question time and adding them to an LLM's prompt, so answers can draw on current, checkable sources without retraining. Landmark · leads to 0 Foundation Model A large model pre-trained on broad data at scale that can be adapted to many downstream tasks, such as GPT-style LLMs, BERT or CLIP.

All 118 Language & LLMs terms

Vision & Multimodal

54 terms · 6 landmarks

Seeing, generating, and mixing images, video, and audio.

Landmark · leads to 16 Computer Vision The field of AI that gets computers to extract meaning from images and video: what is in them, where it is, and how it moves. Landmark · leads to 8 Object Detection Finding every object of interest in an image and giving each a class label, a confidence score and a bounding box. Landmark · leads to 3 Image Classification Assigning one label from a fixed set of categories to a whole image, such as "cat" or "defective part"; a core computer vision task. Landmark · leads to 3 Image Generation Creating new images, often from a text prompt, with generative models such as GANs, VAEs and diffusion models that learn to turn random noise into realistic pictures. Landmark · leads to 2 Diffusion Model A generative model trained to remove noise a step at a time, so it can turn pure random noise into a new image, audio clip or other sample. Landmark · leads to 2 Semantic Segmentation Labelling every pixel in an image with a class, such as road, car or sky, so the output is a map of what is where rather than a single tag.

All 54 Vision & Multimodal terms

Agents & RL

32 terms · 6 landmarks

Reinforcement learning, planning, tool use, and agents that act.

Landmark · leads to 16 Reinforcement Learning Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies. Landmark · leads to 4 Policy The rule an RL agent uses to choose actions: a mapping from each state to an action, or to a probability distribution over actions. Landmark · leads to 4 Reward The single number an environment sends back after each action, telling a reinforcement learning agent how good that step was; the agent learns to maximize its long-run total. Landmark · leads to 3 Agent In reinforcement learning, the learner and decision-maker that observes an environment, takes actions and adjusts its behaviour to maximize cumulative reward. Landmark · leads to 2 Tool Use A language model asking the application around it to run a function, such as search, a calculator or an API, then using the result in its answer. Landmark · leads to 0 AI Agent A system where a large language model decides its own next steps in a loop: calling tools, reading the results, and continuing until the task is done.

All 32 Agents & RL terms

Shipping AI

71 terms · 1 landmarks

Serving, infrastructure, efficiency, safety, and running AI for real.

Landmark · leads to 12 Inference Running a trained model on new inputs to get predictions, with its weights frozen: the stage of a model's life that users actually interact with.

All 71 Shipping AI terms