25

If I'm not mistaken you're looking for Roko's Basilisk, in which an otherwise benevolent future AI system tortures simulations of those who did not work to bring the system into existence


10

I believe the term you are looking for is "(technological) singularity". https://en.wikipedia.org/wiki/Technological_singularity


7

The MDP defines the environment (which corresponds to the task that you need to solve), so it defines e.g. the states of the environment, the actions that you can take in those states, the probabilities of transitioning from one state to the other and the probabilities of getting a reward when you take a certain action in a certain state. The policy ...


6

The likely expression you are looking for is AI takeover, which is a common topic in science fiction movies, such as 2001: A Space Odyssey and The Matrix, and popular culture. Although the AI takeover is an unlikely scenario in the next years, certain scientists, such as Stephen Hawking, have expressed concerns about it and some philosophers, especially Nick ...


6

A stochastic process has the Markov property if the probability distribution of future states conditioned on both the present and past states depends only on the present state or, more formally, the following equality holds. $$ p(s_{t+1} \mid s_{t}, s_{t-1:1}) = p(s_{t+1} \mid s_{t}), \forall t $$ The hidden Markov model (HMM) is an example of a model ...


5

There is no strict definition of suitability of an activation function for neural networks. Instead there are a number of desirable traits, and functions that don't meet them or come close enough may perform badly in general (but those functions may still work in specific cases) If you are using gradient descent as a training method, then differentiability ...


5

Not quite. You are missing the reward at time step $t+1$. The definition you are looking for is (leaving out the $\pi$ subscripts for ease of notation) $$q(s,a) = \mathbb{E}[R_{t+1} + \gamma v(s') | S_t=s,A_t=a] = \sum_{r,s'}(r + v(s'))p(s',r|s,a)\;.$$ Because $q(s,a)$ relates to expected returns at time $t$, and returns are defined as $G_t = \sum_{b = 0}...


5

Reinforcement Learning can be explained by a few equations. However I assume that this is not what you are looking at since the explanation should be for someone having a non-STEM background. Not to say non-STEM folks are not able to understand math equations, but intuition comes easier with words and examples in my opinion. Reinforcement Learning is about ...


5

The famous book Reinforcement learning: an introduction by Sutton and Barto provides an intuitive description of reinforcement learning (that everyone is possibly able to understand). Reinforcement learning is learning what to do — how to map situations to actions — so as to maximize a numerical reward signal. The learner is not told which actions to take, ...


5

Humans are set loose in the world and go about their days doing stuff. Whenever they do specific things, their brain sends them good signals (endorphins, joy, etc.) or bad signals (pain, sadness, etc.). They learn through these signals which things they should be doing and which things they shouldn't be doing. Sometimes the signal is immediate and you know ...


4

As you can see from the picture above (In courtesy to this guy post). Deep learning is a field inside machine learning which involves using deep neural networks to solve machine learning problems. Tensorflow.js and Brain.js are software architectures built in order to assemble and develop ML models inside the browser. If you would like to delve into this ...


4

As far as I know, the sigmoid is often used as the activation function of the output layer mainly because it is a convenient way of producing an output $p \in [0, 1]$, which can be interpreted as a probability, although that can be misleading or even wrong (if you interpret it as an uncertainty too). You may require the output of the neural network to be a ...


4

A surrogate model is a simplified model. It is a mapping $y_S=f_S(x)$ that approximates the original model $y=f(x)$, in a given domain, reasonably well. Source: Engineering Design via Surrogate Modelling: A Practical Guide In the context of Bayesian optimization, one wants to optimize a function $y=f(x)$ which is expensive (very time consuming) to evaluate, ...


4

Here is a paper with the mathematical definition of each term: Let Nt,n,σ,L be all target functions that can be implemented using a neural network of depth t, size n, activation function σ, and when we restrict the input weights of each neuron to be |w|1 + |b| ≤ L.


3

As far as I know, no true artificial general intelligent system (AGI) has been implemented or is practically useful. Yes, there is Sophia and similar robots that may look like an AGI, but they aren't really AGI systems, as they lack several capabilities that we humans have and they can't really adapt to new circumstances. Despite their success, AlphaGo and ...


3

As far as I know, there isn't a "specified correct way". The whole idea is that you want the population to converge and increase the sample rate in that more optimal looking place. What works best all depends upon your fitness landscape. You could also crossover by doing something like crossover_point = random_number_size_genome child[:] = parent_a[:...


3

What is the difference between the definition of a stationary policy in reinforcement learning and contextual bandit? There is no difference. A policy decides which action to take in each state. This is usually split into deterministic policies of the form $\pi(s) : \mathcal{S} \rightarrow \mathcal{A}$ and stochastic policies of the form $\pi(s|a) : \...


3

Here's a definition by Tom Mitchel (1997): Computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E. So, the programmer gives some instructions/rules to the computer, so that it can learn how to solve the problem from the ...


3

I think you are looking at it from the wrong direction, min-max is just a planning algorithm, decision strategy, in the sense that you are describing other algorithms/methods it does not have a category. For example, you have negamax algorithm which is in a sense the same thing the Monte Carlo Search Tree is to Monte Carlo. Min-max category is game theory ...


3

There's some useful information in your description, but that's just a very vague description of how neural networks with sigmoid activation functions are trained. Moreover, there are many other AI systems apart from neural networks (such as support vector machines, expert systems, etc.), which, of course, I cannot exhaustively list here. Is my ...


3

The Turing test is a test proposed by Alan Turing (one of the founders of computer science and artificial intelligence), described in section 1 of paper Computing Machinery and Intelligence (1950), to answer the question Can machines think? More precisely, the Turing test was originally framed as an interactive quiz (denoted as the imitation game by Turing)...


2

Graph Neural Networks The term Graph Neural Network, in its broadest sense, refers to any Neural Network designed to take graph structured data as its input: To cover a broader range of methods, this survey considers GNNs as all deep learning approaches for graph data. A Comprehensive Survey on Graph Neural Networks, Wu et al (2019) However the ...


2

I think I would never say that neural networks are iterative methods. I would say that iterative methods (e.g. gradient descent) are used to train neural networks (which can be thought of as linear and non-linear models, but mainly non-linear), which is quite different. Maybe you should or wanted to say that deep learning is an area of study where iterative ...


2

The paper you are citing is the paper that introduced the cascaded convolution neural network. In fact, in this paper, the authors say To realize 3DDFA, we propose to combine two achievements in recent years, namely, Cascaded Regression and the Convolutional Neural Network (CNN). This combination requires the introduction of a new input feature which ...


2

Data preprocessing consists of all those techniques used to generate the final datasets (with an appropriate size, structure, and format) for the machine learning algorithms or models. Data acquisition should not be part of data preprocessing, but the step preceding it, which gathers the raw data (which may e.g. be noisy). The book Data Preprocessing in ...


2

Philosophically, my own research has led me to understand AI as any artifact that makes a decision. This is because the etymology of "intelligence" strongly implies "selecting between alternatives", and these meanings are baked in all the way back to the proto-Indo-European. (Degree of intelligence, or "strength" is merely a measure of utility, typically ...


2

AI is not a simple term. There are different types, ranging from the most simplistic rule-based AI to black-box AI's so complicated it's unreasonable for a human to understand exactly what they're doing. There's no pseudocode that if used in a program automatically constitutes it as an AI. It's not that black and white. But I can give examples: Here's a ...


2

If it is not defined otherwise, testing is the phase where the model is passed with new data instances to derive the score of the test set. It should not be confused with validation set. A validation dataset is a sample of data held back from training your model that is used to give an estimate of model skill while tuning model’s hyperparameters during ...


2

Keeping this taxonomy intact for model-based Dynamic programming algorithms, I would argue that value iteration is a Actor only approach, and policy iteration is a Actor-Critic approach. However, not many people discuss the term Actor-Critic when referring to Policy Iteration. How come? Both policy iteration and value iteration are value-based approaches. ...


2

Aside from the points raised in nbro's answer, I'd like to point out that for a single MDP (a single instance of a "problem"), it may be sensible to study it from perspectives that include no policy at all, or multiple different policies. For instance, if I have an MDP, I may be interested in studying it by looking at various inherent properties of the ...


Only top voted, non community-wiki answers of a minimum length are eligible