From 1d0e69942b3ca5012bb78545a2019e804a2ccf8f Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 10:25:36 +0200 Subject: [PATCH 1/9] Added AI --- glossary.yml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index a48b98b4..f757ae97 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10110,4 +10110,13 @@ term: "non-parametric (statistics)" def: > A branch of statistical tests which do not assume a known distribution of the population which the samples were taken from (Kruskal-Wallis and Dunn test are examples of non-parametric tests). - +- slug: artificial_intelligence + ref: + - nlp + - + en: + term: "artificial intelligence (AI)" + def: > + Intelligence demonstrated by machines, as opposed to humans or other animals. AI can be + exhibited through perceiving, synthesizing and inference of information. Example tasks include + natural language processing, computer vision, and machine learning. From 755870137966dffffb84489141b552a3367d9dcb Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 10:48:57 +0200 Subject: [PATCH 2/9] cnn --- glossary.yml | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/glossary.yml b/glossary.yml index f757ae97..1550a279 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10113,10 +10113,24 @@ - slug: artificial_intelligence ref: - nlp - - + - ma en: term: "artificial intelligence (AI)" def: > Intelligence demonstrated by machines, as opposed to humans or other animals. AI can be exhibited through perceiving, synthesizing and inference of information. Example tasks include - natural language processing, computer vision, and machine learning. + [natural language processing](#nlp), computer vision, and [machine learning] + (#machine_learning). + +- slug: cnn + ref: + - deep_learning + - backpropagation + - perceptron + - neural_network + - machine_learning + term: "convolutional neural network (cnn)" + def: > + A class of artificial neural network that is primarily used to analyze images. A CNN has layers + that perform convolutions, where a filter is shifted over the data, instead of the general + matrix multiplications that we see in fully connected neural network layers. \ No newline at end of file From a9cf5352c9421d4271c8656ca522f7f3f9b586fb Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 10:53:41 +0200 Subject: [PATCH 3/9] RNN --- glossary.yml | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index 1550a279..8a8df963 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10133,4 +10133,17 @@ def: > A class of artificial neural network that is primarily used to analyze images. A CNN has layers that perform convolutions, where a filter is shifted over the data, instead of the general - matrix multiplications that we see in fully connected neural network layers. \ No newline at end of file + matrix multiplications that we see in fully connected neural network layers. + +- slug: rnn + ref: + - deep_learning + - backpropagation + - perceptron + - neural_network + - machine_learning + term: recurrent neural network + def: > + A class of [artificial neural networks](#neural_network) where connections between nodes can + create a cycle. This allows the network to exhibit behavior that is dynamic over time. This + type of network is applicable to tasks like speech and handwriting recognition. \ No newline at end of file From 2cf133e420a71e3f4377b7f6d76e5f4ffa7dd736 Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 11:57:02 +0200 Subject: [PATCH 4/9] epoch --- glossary.yml | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index 8a8df963..f1c43470 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10146,4 +10146,17 @@ def: > A class of [artificial neural networks](#neural_network) where connections between nodes can create a cycle. This allows the network to exhibit behavior that is dynamic over time. This - type of network is applicable to tasks like speech and handwriting recognition. \ No newline at end of file + type of network is applicable to tasks like speech and handwriting recognition. + +- slug: epoch_dl + ref: + - deep_learning + - backpropagation + - perceptron + - neural_network + - machine_learning + term: epoch (deep learning) + def: > + In [deep learning](#deep_learning), an epoch is one cycle in the deep learning process where all + the training data has been fed to the algorithm once. Training a deep neural networks usually + consists of multiple epochs. \ No newline at end of file From a0c7a3bc4a1351404a9c6b1c9ef099b72e932b80 Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 13:00:56 +0200 Subject: [PATCH 5/9] Learning rate --- glossary.yml | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index f1c43470..4159f624 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10159,4 +10159,18 @@ def: > In [deep learning](#deep_learning), an epoch is one cycle in the deep learning process where all the training data has been fed to the algorithm once. Training a deep neural networks usually - consists of multiple epochs. \ No newline at end of file + consists of multiple epochs. + +- slug: learning_rate + ref: + - deep_learning + - backpropagation + - perceptron + - neural_network + - machine_learning + def: > + In [artificial neural networks](#neural_network), the learning rate is a hyper-parameter that + determines the pace at which the network adjusts the weights to move down the loss gradient. + A large learning rate can speed up training, but the network might overshoot and miss the + minimum. A small learning rate will overshoot less, but will be slower. It can also get more + easily stuck in local minima. From e150abe5e15f6d94f73dfb8f1f960fca1c2aa6ca Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 13:44:32 +0200 Subject: [PATCH 6/9] class imbalance --- glossary.yml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/glossary.yml b/glossary.yml index 4159f624..8f32ee79 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10174,3 +10174,11 @@ A large learning rate can speed up training, but the network might overshoot and miss the minimum. A small learning rate will overshoot less, but will be slower. It can also get more easily stuck in local minima. + +- slug: class_imbalance + ref: + - machine_learning + def: + Class imbalance refers to the problem [machine learning](machine_learning) where there is an + unequal distribution of classes in the dataset. + From 7ae075e48a5dac2b882bc4496e95a9d3ef531cb3 Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 13:51:17 +0200 Subject: [PATCH 7/9] Hidden layer --- glossary.yml | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index 8f32ee79..c127b3b2 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10178,7 +10178,17 @@ - slug: class_imbalance ref: - machine_learning - def: + def: > Class imbalance refers to the problem [machine learning](machine_learning) where there is an unequal distribution of classes in the dataset. +- slug: hidden_layer + ref: + - neural_network + - machine_learning + - deep_learning + - perceptron + def: > + A hidden layer in a [neural network](#neural_network) refers to the layers of neurons that are + not directly connected to input or output. The layers are "hidden" because you do not directly + observe their input and output values. From 50dbf879c220c7b0ca4f0af9ac292d69ec335f55 Mon Sep 17 00:00:00 2001 From: Djura Smits Date: Wed, 17 May 2023 13:53:39 +0200 Subject: [PATCH 8/9] ma -> machine_learning --- glossary.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index c127b3b2..2894d292 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10113,7 +10113,7 @@ - slug: artificial_intelligence ref: - nlp - - ma + - machine_learning en: term: "artificial intelligence (AI)" def: > From d504b3706a564b4fd3cd9b2ab0f5f79c011a69d3 Mon Sep 17 00:00:00 2001 From: dsmits Date: Wed, 16 Aug 2023 09:05:54 +0200 Subject: [PATCH 9/9] Update glossary.yml Co-authored-by: Sven van der Burg --- glossary.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/glossary.yml b/glossary.yml index 2894d292..3579553d 100644 --- a/glossary.yml +++ b/glossary.yml @@ -10179,7 +10179,7 @@ ref: - machine_learning def: > - Class imbalance refers to the problem [machine learning](machine_learning) where there is an + Class imbalance refers to the problem in [machine learning](machine_learning) where there is an unequal distribution of classes in the dataset. - slug: hidden_layer