Publication

A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission

Related concepts (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Deep reinforcement learning

Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.

Wire chamber

A wire chamber or multi-wire proportional chamber is a type of proportional counter that detects charged particles and photons and can give positional information on their trajectory, by tracking the trails of gaseous ionization. The multi-wire chamber uses an array of wires at high voltage (anode), which run through a chamber with conductive walls held at ground potential (cathode). Alternatively, the wires may be at ground potential and the cathode held at a high negative voltage; the important thing is that a uniform electric field draws extra electrons or negative ions to the anode wires with little lateral motion.

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.

Explainable artificial intelligence

Explainable AI (XAI), also known as Interpretable AI, or Explainable Machine Learning (XML), either refers to an AI system over which it is possible for humans to retain intellectual oversight, or to the methods to achieve this. The main focus is usually on the reasoning behind the decisions or predictions made by the AI which are made more understandable and transparent. XAI counters the "black box" tendency of machine learning, where even the AI's designers cannot explain why it arrived at a specific decision.

Generative adversarial network

A generative adversarial network (GAN) is a class of machine learning framework and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss. Given a training set, this technique learns to generate new data with the same statistics as the training set.

Particle identification

Particle identification is the process of using information left by a particle passing through a particle detector to identify the type of particle. Particle identification reduces backgrounds and improves measurement resolutions, and is essential to many analyses at particle detectors. Charged particles have been identified using a variety of techniques. All methods rely on a measurement of the momentum in a tracking chamber combined with a measurement of the velocity to determine the charged particle mass, and therefore its identity.

Proton

A proton is a stable subatomic particle, symbol _Proton, H+, or 1H+ with a positive electric charge of +1 e (elementary charge). Its mass is slightly less than that of a neutron and 1,836 times the mass of an electron (the proton-to-electron mass ratio). Protons and neutrons, each with masses of approximately one atomic mass unit, are jointly referred to as "nucleons" (particles present in atomic nuclei). One or more protons are present in the nucleus of every atom.

Alpha particle

Alpha particles, also called alpha rays or alpha radiation, consist of two protons and two neutrons bound together into a particle identical to a helium-4 nucleus. They are generally produced in the process of alpha decay, but may also be produced in other ways. Alpha particles are named after the first letter in the Greek alphabet, α. The symbol for the alpha particle is α or α2+. Because they are identical to helium nuclei, they are also sometimes written as He2+ or 42He2+ indicating a helium ion with a +2 charge (missing its two electrons).

Learning rate

In machine learning and statistics, the learning rate is a tuning parameter in an optimization algorithm that determines the step size at each iteration while moving toward a minimum of a loss function. Since it influences to what extent newly acquired information overrides old information, it metaphorically represents the speed at which a machine learning model "learns". In the adaptive control literature, the learning rate is commonly referred to as gain. In setting a learning rate, there is a trade-off between the rate of convergence and overshooting.