60

Machine learning has been defined by many people in multiple (often similar) ways [1, 2]. One definition says that machine learning (ML) is the field of study that gives computers the ability to learn without being explicitly programmed. Given the above definition, we might say that machine learning is geared towards problems for which we have (lots of) data ...


50

As complexity rises, precise statements lose meaning and meaningful statements lose precision. ( Lofti Zadeh ). Fuzzy logic deals with reasoning that is approximate rather than fixed and exact. This may make the reasoning more meaningful for a human: Fuzzy logic is an extension of Boolean logic by Lotfi Zadeh in 1965 based on the mathematical theory of ...


38

TLDR: The convolutional-neural-network is a subclass of neural-networks which have at least one convolution layer. They are great for capturing local information (e.g. neighbor pixels in an image or surrounding words in a text) as well as reducing the complexity of the model (faster training, needs fewer samples, reduces the chance of overfitting). See ...


36

The terms strong and weak don't actually refer to processing, or optimization power, or any interpretation leading to "strong AI" being stronger than "weak AI". It holds conveniently in practice, but the terms come from elsewhere. In 1980, John Searle coined the following statements: AI hypothesis, strong form: an AI system can think and have a mind (in the ...


31

The difference is mostly in the number of layers. For a long time, it was believed that "1-2 hidden layers are enough for most tasks" and it was impractical to use more than that, because training neural networks can be very computationally demanding. Nowadays, computers are capable of much more, so people have started to use networks with more layers and ...


31

By "company A has a large human face database so that it can train its facial recognition program more efficiently" the article probably means that there is a training dataset $S$ of the form $$ S = \{ (\mathbf{x}_1, y_1), \dots,(\mathbf{x}_N, y_N) \} $$ where $\mathbf{x}_i$ is an image of the face of the $i$th human and $y_i$ (which is often called a ...


26

The bottleneck in a neural network is just a layer with fewer neurons than the layer below or above it. Having such a layer encourages the network to compress feature representations to best fit in the available space, in order to get the best loss during training. In a CNN (such as Google's Inception network), bottleneck layers are added to reduce the ...


24

The notation I'll be using is from two different lectures by David Silver and is also informed by these slides. The expected Bellman equation is $$v_\pi(s) = \sum_{a\in \cal{A}} \pi(a|s) \left(\cal{R}_s^a + \gamma\sum_{s' \in \cal{S}} \cal{P}_{ss'}^a v_\pi(s')\right) \tag 1$$ If we let $$\cal{P}_{ss'}^\pi = \sum\limits_{a \in \cal{A}} \pi(a|s)\cal{P}_{ss'}^a ...


23

Machine learning is a subset of artificial intelligence. Roughly speaking, it corresponds to its learning side. There is no "official" definitions, boundaries are a bit fuzzy.


22

Fuzzy logic is based on regular boolean logic. Boolean logic means you are working with truth values of either true or false (or 1 or 0 if you prefer). Fuzzy logic is the same apart from you can have truth values that are in-between true and false, that is to say, you are working with any number between 0 (inclusive) and 1 (inclusive). The fact that you can ...


16

Artificial intelligence According to the book Artificial Intelligence: A Modern Approach (section 1.1), artificial intelligence (AI) has been defined in multiple ways, which can be organized into 4 categories. Thinking Humanly Thinking Rationally Acting Humanly Acting Rationally Figure 1.1 (of the same book) contains 8 definitions (by renowned people like ...


15

"Backprop" is the same as "backpropagation": it's just a shorter way to say it. It is sometimes abbreviated as "BP".


15

Convolutional Neural Networks (CNNs) are neural networks with architectural constraints to reduce computational complexity and ensure translational invariance (the network interprets input patterns the same regardless of translation— in terms of image recognition: a banana is a banana regardless of where it is in the image). Convolutional Neural Networks ...


15

Actor-Critic is not just a single algorithm, it should be viewed as a "family" of related techniques. They're all techniques based on the policy gradient theorem, which train some form of critic that computes some form of value estimate to plug into the update rule as a lower-variance replacement for the returns at the end of an episode. They all perform "...


14

Sometimes observation and state overlap completely, which is convenient. However, there is no reason to expect it in all cases, and that's where interesting problems occur. Reinforcement learning theory is based on Markov Decision Processes. This leads to a formal definition of state. Most importantly, the state must have the Markov property. Which means ...


13

John McCarthy (1927 - 2011) was an American computer scientist. A pioneer in the foundations of artificial intelligence research, he coined the term "artificial intelligence". He was one of the creators of the (original) Lisp programming language, which was quite involved in early AI research in the 1960s and 1970s. He coined the term in 1955, and organized ...


12

The machine learning is a sub-set of artificial intelligence which is only a small part of its potential. It's a specific way to implement AI largely focused on statistical/probabilistic techniques and evolutionary techniques.Q Artificial intelligence Artificial intelligence is 'the theory and development of computer systems able to perform tasks normally ...


12

A deep neural network (DNN) is nothing but a neural network which has multiple layers, where multiple can be subjective. IMHO, any network which has 6 or 7 or more layers is considered deep. So, the above would form a very basic definition of a deep network.


12

Embedding vs Latent Space Due to Machine Learning's recent and rapid renaissance, and the fact that it draws from many distinct areas of mathematics, statistics, and computer science, it often has a number of different terms for the same or similar concepts. "Latent space" and "embedding" both refer to an (often lower-dimensional) ...


12

The dynamic programming algorithms (like policy iteration and value iteration) are often presented in the context of reinforcement learning (in particular, in the book Reinforcement Learning: An Introduction by Barto and Sutton) because they are very related to reinforcement learning algorithms, like $Q$-learning. They are all based on the assumption that ...


12

Active learning (AL) is a weakly supervised learning (WSL) technique where you can have both labelled and unlabelled data [1]. The main idea behind AL is that the learner (or learning algorithm) can query an "oracle" (e.g. a human) to label some unlabelled instances. AL is similar to semi-supervised learning (SSL), which is also a WSL technique, ...


10

A deep neural network is just a (feed-forward) neural network with many layers. However, deep belief networks, Deep Boltzmann networks, etc., are not considered (debatable) deep neural networks, as their topology is different (i.e. they have undirected networks in their topology). See also this: https://stats.stackexchange.com/a/59854/84191.


10

In the blog post Building powerful image classification models using very little data, bottleneck features are mentioned. What are the bottleneck features? It's clearly written in the link you gave the "bottleneck features" from the VGG16 model: the last activation maps before the fully-connected layers. Do they change with the architecture that is used? ...


10

Imagine, you want to re-compute the last layer of a pre-trained model : Input->[Freezed-Layers]->[Last-Layer-To-Re-Compute]->Output To train [Last-Layer-To-Re-Compute], you need to evaluate outputs of [Freezed-Layers] multiple times for a given input data. In order to save time, you can compute these ouputs only once. Input#1->[Freezed-Layers]...


10

In answer that you linked, I may have used an informal definition of "trajectory", but essentially the same thing as the quote. A "trajectory" is the sequence of what has happened (in terms of state, action, reward) over a set of contiguous timestamps, from a single episode, or a single part of a continuous problem. So $(s_3, a_3, r_4, s_4, a_4, r_5, s_5, ...


10

The Wikipedia article is more technically correct, in that the term RNN is formally taken to mean "a neural network with recurrent connections", and that includes many architectures that match this description, including LSTMs. However, it is also common to see "RNN" used as a short-hand for a kind of "Vanilla RNN" or "...


9

Many terms have 'mostly' the same meanings, and so the differences are just in emphasis, perspective, or historical descent. People disagree as to which label refers to the superset or the subset; there are people who will call AI a branch of ML and people who will call ML a branch of AI. I typically hear Machine Learning used as a form of 'applied ...


9

An ability that is commonly attributed to intelligence is problem solving. Another one is learning (improving itself from experience). Artificial intelligence can be defined as "replicating intelligence, or parts of it, at least in appearance, inside a computer" (dodging the definition of intelligence itself). Genetic algorithms are computational problem ...


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