Machine learning

Overview

Machine learning (ML) is the part of artificial intelligence in which a system learns from training data specific to the problem, instead of following rules a person wrote 2104.05314 p. 3. Artificial intelligence is the wider goal: machines that match or beat human decision-making on complex tasks 2104.05314 p. 3. Deep learning is a further subset, built on neural networks with many layers 2104.05314 p. 3.

The review's motivation is data. Electronic markets produce much unstructured data, such as time series, images and text. Finding patterns in it by hand would exceed human capacity, so the authors argue for automated model building 2104.05314 p. 4.

This page rests on two sources. The first is a conceptual review with no equations, algorithms, benchmarks or code 2104.05314 p. 1. It gives vocabulary and a list of practical risks. The second is an open textbook that teaches the field from linear algebra and probability onward, with runnable code. It introduces no new method of its own 2106.11342 §1. It supplies the methods and worked examples that the review leaves out. The two are covered under Variants and in the sections below.

Variants

Types of learning

The review splits ML into three types, chosen by the problem and the data 2104.05314 tab. 1 2104.05314 p. 3:

• Supervised learning. The training inputs come with labelled target values. The goal is to predict a number (regression) or a class (classification).
• Unsupervised learning. The inputs have no labels. The goal is to find structure: groups (clustering) or a compact representation.
• Reinforcement learning. The learner gets a goal, allowed actions, constraints and a reward signal. It learns by trial and error to maximise reward.

Card: Machine learning and deep learning.

The textbook covers two of these types with methods and code. Its supervised chapters start from linear networks for regression and classification 2106.11342 §3–§4. Its reinforcement learning chapter starts from Markov decision processes 2106.11342 §17. Card: Dive into Deep Learning.

Ways to build a model

The review compares three paradigms, using the four aspects of model building described below 2104.05314 fig. 2 2104.05314 p. 4–5:

• Explicit programming. A person writes the rules. There is no learning step 2104.05314 p. 4.
• Shallow machine learning. A person designs the features, and a learning algorithm fits the model on them. The review names decision trees and support vector machines as examples 2104.05314 p. 5.
• Deep learning. Feature learning and model building happen in one pipeline 2104.05314 p. 5. See deep learning.

The review says the boundary between shallow and deep is not exact 2104.05314 p. 4. The textbook treats the deep side in more depth: multilayer perceptrons come first 2106.11342 §5, followed by convolutional networks 2106.11342 §7 and attention with transformers 2106.11342 §11.

When to use which

The review gives qualitative guidance only. The textbook gives no selection rules, so its row below only points to where the methods are taught. Each row states what the cited source says.

Model-building process

The review describes four aspects of building an analytical model 2104.05314 p. 4 2104.05314 fig. 2:

1. Data input. Collect the raw data, which may be structured or not.
2. Feature extraction. Derive properties from the raw input that keep the information needed to separate classes. Manual design is one option; deep networks learn features hierarchically, from simple parts to complex ones 2104.05314 p. 4–5.
3. Model building. A learning algorithm finds the patterns that matter for the task. A decision tree splits the data into more homogeneous partitions. A support vector machine finds a separating hyperplane, often after mapping the data into a higher-dimensional space 2104.05314 p. 5.
4. Model assessment. Judge the model on performance, computational resources and interpretability 2104.05314 p. 5.

Assessment

• Out-of-sample performance. Use k-fold cross-validation, which guards against overfitting and gives out-of-sample estimates 2104.05314 p. 5. The textbook covers generalization alongside dropout in its multilayer perceptron chapter 2106.11342 §5.
• Metrics. For classification the review names accuracy, recall, precision and F1. For regression it names RMSE and MAPE 2104.05314 p. 5–6.
• Unequal error costs. Where mistakes cost different amounts, as in fraud detection, the review suggests cost-sensitive measures such as the average cost per prediction 2104.05314 p. 6.
• Cost. Weigh model complexity, such as the number of trainable parameters, and computational cost, such as memory and inference time [arxiv:2104.05314 p. 6–7]. The textbook gives computational performance its own chapter, on compilers, asynchrony, hardware, multi-GPU training and parameter servers 2106.11342 §13.

Risks in practice

The review lists four challenges for intelligent systems 2104.05314 p. 7–9:

• The triangle of architecture, hyperparameters and training data. These trade off accuracy, memory, speed and cost 2104.05314 p. 7.
• Bias and drift. Data can carry bias, and its distribution can change over time. The review calls concept drift sudden, gradual or recurring, and hard to detect. It names manual checks and periodic retraining as current practice, and lists data poisoning as a threat 2104.05314 p. 7–8. See data poisoning.
• Unpredictability and explainability. Models can behave in ways that are hard to predict, so the review asks for explainability 2104.05314 p. 8. See interpretable machine learning.
• Resource limits and transfer learning. Pre-trained models can save resources, but the review names backdoors in them as a risk 2104.05314 p. 8–9. See transfer learning.

Implementation sketch

The review defines no procedure. The sketch restates its four aspects and its assessment step. It is not an algorithm from the paper. The textbook's base trainer follows the same shape: a training pass that updates the model, then a validation pass with gradients turned off torch.py. The book's chapters implement the standard methods they cover; they do not define a single procedure.

# Build and assess a model  [arxiv:2104.05314 p. 4–7]
# Input:  raw data, labels for supervised tasks
# Output: a fitted model and its assessment

def build_model(raw_data, labels):
    # Data input and feature extraction  [p. 4–5]
    features = extract_features(raw_data)
    # Model building: a learning algorithm fits the features  [p. 5]
    model = fit_learning_algorithm(features, labels)
    return model

def assess(model, data, labels, k):
    # k-fold cross-validation guards against overfitting  [p. 5]
    scores = k_fold_scores(model, data, labels, k)
    # Report performance, cost and interpretability together  [p. 5–7]
    return {
        "metrics": scores,                    # e.g. F1, RMSE  [p. 5–6]
        "memory_and_inference_time": cost(model),
        "interpretability": explain_notes(model),
    }

Contradictions

None known. The two sources answer different questions: the review gives vocabulary and risks, and the textbook gives methods and code. Inside the review, interpretability is stated loosely. It calls some shallow models inherently interpretable and most advanced models opaque unless explained, yet it also says shallow models can be more interpretable than deep networks 2104.05314 p. 4. None of these claims is measured.

Papers

• Machine learning and deep learning: a conceptual review that defines AI, machine learning and deep learning, contrasts three modelling paradigms, and lists deployment challenges. No experiments.
• Dive into Deep Learning: an open textbook that pairs text, maths and runnable notebooks, from linear networks through transformers to reinforcement learning. It introduces no new algorithm, and its book benchmarks are not stated.