Machine Learning in Geomechanics 1 (eBook)

Overview of Machine Learning, Unervised Learning, Regression, Classification and Artificial Neural Networks

Ioannis Stefanou, Félix Darve (Herausgeber)

eBook Download: EPUB

2024
356 Seiten
Wiley-Iste (Verlag)
978-1-394-32562-7 (ISBN)

Infos

Machine learning has led to incredible achievements in many different fields of science and technology. These varied methods of machine learning all offer powerful new tools to scientists and engineers and open new paths in geomechanics.

The two volumes of Machine Learning in Geomechanics aim to demystify machine learning. They present the main methods and provide examples of its applications in mechanics and geomechanics. Most of the chapters provide a pedagogical introduction to the most important methods of machine learning and uncover the fundamental notions underlying them.

Building from the simplest to the most sophisticated methods of machine learning, the books give several hands-on examples of coding to assist readers in understanding both the methods and their potential and identifying possible pitfalls.

Ioannis Stefanou is Professor at ECN, France, and leads several geomechanics projects. His main research interests include mechanics, geomechanics, control, induced seismicity and machine learning.

Félix Darve is Emeritus Professor at the Soils Solids Structures Risks (3SR) laboratory, Grenoble-INP, Grenoble Alpes University, France. His research focuses on computational geomechanics.

Textauszug

1
Overview of Machine Learning in Geomechanics

Ioannis STEFANOU

GeM, UMR 6183, CNRS, Ecole Centrale Nantes, Nantes Université, France

1.1. What exactly is machine learning?

One of the best methods for making a puppy learn its name is to play the name game:

1) Take your puppy to a quiet place and gain its attention by calling its name in a happy and reassuring tone (e.g. “LoupI look at me!” or “LoupI come here!”).

2) As soon as you have gained its attention, reward it with a treat to encourage its good behavior.

3) Repeat this process several times until your puppy has learned to respond to its name.

In the above iterative process, the puppy learns from experience that reacting when you call its name is a good thing. By repeating this process, the puppy recognizes the pattern between similar, but not identical, vocal signals of its name (training data) and associates them with a specific behavior (task).

Many cognitive processes of humans involve a similar way for associating patterns with specific reactions; for instance, see how we learn to drive a car, speak a foreign language or even understand how a geomaterial behaves!

Machine learning (ML) is an anthropomorphic extension of the above process of “learning” to a computer program, that is, to the machine. By learning, the machine will progressively improve its performance in executing a specific task. According to Mitchell (1997), ML can be defined as follows:

A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.

The whole set of examples that the computer will use during learning is the training set, while each training example is called a training instance or sample. The whole process of learning is called training. The training set is usually distinguished into training data, validation data and test data. More details about those sets and their importance will be given in section 1.5 and in Chapters 2 and 5 of volume 1.

A popular example showing the power of ML was AlphaGo, a ML program, which beat the human world champion of Go (see also (Silver et al. 2016) and Chapter 4 of volume 2 on reinforcement learning). Go is a strategy board game for two players in which the aim is to cover more territory than the opponent (see Figure 1.1). Despite its relatively simple rules, Go is extremely complex. The state-space complexity of Go, that is, the number of legal game positions reachable from the initial position of the game (Allis 1994), is of the order of 10170 (Tromp and Farnebäck 2007), which is much higher than that of chess, which is of the order of 1044 (Shannon 1950), and certainly higher than the number of atoms in the universe. This makes Go a great challenge for ML algorithms.

Figure 1.1. Eighteen times Go world champion Lee Sedoll playing with the machine (courtesy: Lee Jin-man/AP, The New Yorker, https://www.newyorker.com/tech/annals-of-technology/alphago-lee-sedol-and-the-reassuring-future-of-humans-and-machines)

Applying the above-mentioned definition in an ML program for Go, the performance (P) will be measured by the ability of the machine to beat its opponent by gaining experience (E) by executing multiple times the task (T), which is playing the game with itself. Experience can be also obtained by processing existing games of other (human) players.

Another recent popular example of ML is the ChatGPT chatbot developed by OpenAI. ChatGPT was released in November 2022 and provoked a massive public reaction. Let us see what it answers when we ask it to describe itself and what it knows about ALERT Geomaterials.

Ioannis: Describe yourself.

ChatGPT: I am ChatGPT, an AI language model developed by OpenAI. I have been trained on a vast amount of text data from the internet, books and other sources. My purpose is to assist users in generating human-like text responses and providing information on a wide range of topics.

I don’t have a physical form or personal experiences like humans do, but I can understand and generate text in multiple languages. I strive to provide helpful and accurate responses to the best of my abilities, drawing upon the knowledge I have acquired during my training.

I can engage in conversations, answer questions, offer explanations and assist with various tasks. However, please keep in mind that while I strive for accuracy, I may occasionally generate incorrect or incomplete information. It’s always a good idea to verify important details from reliable sources.

Overall, I am here to assist and provide information to the best of my abilities. Feel free to ask me anything you’d like to know or engage in a conversation on any topic of your interest.

Ioannis: How do you work?

ChatGPT: As an AI language model, my functioning can be divided into two main phases: training and inference.

Training: During the training phase, large amounts of text data are used to train the model. In the case of GPT models like ChatGPT, this training involves a process called unsupervised learning. The model learns to predict what comes next in a given sequence of text, based on the patterns and relationships it discovers in the training data. By doing this over a vast dataset, the model gradually learns grammar, facts, reasoning abilities and the nuances of human language.

Inference: Once the training is complete, the model moves into the inference phase, where it can generate responses and interact with users. Here’s a simplified overview of how it works during inference:

Input: When you provide a prompt or a message, the model receives it as input. The input can be a question, a statement or any text you want to generate a response to.

Tokenization: The model breaks down the input text into smaller units called tokens. These tokens can represent words, subwords or characters. Tokenization helps the model understand the structure and meaning of the input.

Processing: The tokenized input is then passed through several layers of neural networks. These layers are designed to understand the relationships between the tokens and capture the context and meaning of the text.

Generation: Once the input is processed, the model generates a response. It predicts the most likely next tokens based on the context and the patterns it has learned during training. The generated tokens form the model’s response.

Iteration: The process of tokenization, processing and generation can happen in an iterative manner. The generated response can be further used as input, creating a back-and-forth conversation or a continuous interaction.

It’s important to note that while ChatGPT can generate impressive responses, it may sometimes produce incorrect or nonsensical answers. It doesn’t have real-world experiences or access to current information beyond its knowledge cutoff date. It’s always a good idea to fact-check and verify important information from reliable sources.

Ioannis: What is ALERT Geomaterials in summary?

ChatGPT: In summary, ALERT Geomaterials is an international scientific association dedicated to the study of the mechanics and behavior of geomaterials, including soil, rock and other geological materials. It brings together researchers and professionals in the field of geomechanics and geotechnical engineering to promote collaboration, knowledge exchange and scientific advancements. ALERT Geomaterials organizes workshops, conferences and training courses, providing a platform for researchers to share their findings and discuss topics related to soil and rock mechanics, slope stability, geotechnical engineering, experimental testing and numerical modeling. The association also publishes a journal focused on energy geotechnics and geoenvironmental engineering. Overall, ALERT Geomaterials plays a crucial role in fostering research and innovation in the field of geomaterials.

Impressive! At this point, it becomes quite tempting to let ChatGPT finish this chapter or even both volumes! However, I assure you, we took the necessary time to entirely draft these volumes word by word. Read carefully ChatGPT’s answers. Are all of them correct?

It is straightforward to see how the above definition for ML applies to ChatGPT and to many other applications of ML, such as speech, handwriting, face and object recognition, voice-to-text and vice versa, translation, text auto-correction and auto-completion, spam filtering, computer games, self-driving cars, medicine, forecasting, banking, security, marketing, control problems, engineering and, of course, (geo-)mechanics.

ML is an evolving field of knowledge and involves a plethora of methods and combinations of those. In the next section, we will try to categorize and classify them in groups.

Having described and defined what ML is, it is natural to ask what is artificial intelligence (AI)? ML and AI are closely related and the latter is considered to include the former. The exact definition of AI seems to be a bit foggy for the time being and depends on how we define the...

Produkt-Details

• Erscheint lt. Verlag: 10.10.2024
• Reihe/Serie: ISTE Consignment
• Sprache: englisch
• Themenwelt: Naturwissenschaften ► Geowissenschaften ► Geologie
• Themenwelt: Naturwissenschaften ► Physik / Astronomie
• Schlagworte: Artificial Neural Networks • classification • Geomechanics • machine learning • Regression • Unsupervised Learning
• ISBN-10: 1-394-32562-2 / 1394325622
• ISBN-13: 978-1-394-32562-7 / 9781394325627