Deep Learning, AI and Natural Language Processing mind maps
28 mind maps by 26 users
This page gathers mind maps on machine learning, neural networks and natural language processing. The resources are mainly for university-level study, helping university students explore these topics and teachers find material for their classes. There are over 20 user-made mind maps. Pick a map and follow its branches.
Mind maps
-
183 nodesDeep Learning Applied Mathematics · Machine Learning Basics · Deep Learning Modern ... · Deep Learning Researc...
-
34 nodesVariational Auto-Encoder (VAE) What is it? · Architecture · A little history... · What is it used for? · Learning rules · Some real life experi...
-
32 nodesWord Embeddings Map Word/Document int... · Distributional Semant...
-
19 nodesMachine Learning Supervised Learning · Unsupervised Learning... · Reinforcement Learning
-
28 nodesDCGAN Related Works · Architecture · Training · Validation · Visualizing the inter...
-
37 nodesLEXICAL Features Vocabulary Richness · Word Frequencies · Word N-grams approach · Writing Errors · consist of token-base...
-
72 nodesDeep Learning Feed Neural Network · Convolutional Neural ... · Recurrent Neural Netw... · Introduction · Architectures · Reinforcement Learning
-
35 nodeseScience Neural NLP Tasks · Architectures · Data Representation · Useful Resources · Tools & Frameworks · Use Cases
-
34 nodesSparse Autoencoder What is Sparse Autoen... · History · Activation Function · Mathematical Model · Architecture · Use
-
29 nodesMachine Learning when to use? · supervised · unsupervised · Algorithms · Underfitting · overfitting
-
33 nodesMachine Learning Model Non Functional Requir... · Preprocessing · Vector Representation · Classification
-
95 nodesToken UC1 Credit Sale · Credit Return · Overall Risks Testing... · Credit Void · Credit Adjust · Credit Zero Auth
-
42 nodesSYNTACTIC Features features tend to prod... · require robust and ac... · syntactic information... · authors tend to use s... · Rewrite rule frequencies · Sentence Chunks
-
27 nodesSEMANTIC Features represent basic conce... · full syntactic parsin... · Semantic dependency · Synonym and Hypernym ... · Functional features
-
4 nodesOpen questions on the web & KDS questions Question and answer k... · User Intent · Question Semantic fea...
-
20 nodesMachine Learning for NLP MODELS · Smoothing · HMM · LSTMS · Named Entity Recognition
-
36 nodesMinset Neural Network AI · Ai · Aim · Target audience · python · dataset
-
34 nodessentiment analysis techniques · polarity · scores · data · platforms · Online reputation man...
-
8 nodesBayesian networks Use probability as a ... · Allow the representat... · Is a acyclic graph · The objective is tu c...
-
18 nodesNLP Pre-processing · Information Extraction · Summarization/ QA Sys... · Natural Language Anno... · Classification & Cate... · Empathy Extraction
-
15 nodesThing (47) Explainanability · Deep Learning · Neuroscience (5) · Deep Learning and Kno...
-
12 nodesNLU (1)Discriminative par... · (2)incremental parsing · (3)Semantic parsing · (4)Unsupervised parsing · (5)Unsupervised tagging · (6)Distributional sem...
-
11 nodesSentiment analysis Implementation · Approaches
-
22 nodesText Summarizer Python · Extractive Summary
-
23 nodesMachine Learning AI · applications · learning kinds · knowledge
-
13 nodesHotel Review Programming Language · WebForms · Sentiment Analysis
-
6 nodesTokenization Product Offering
-
6 nodesDeep Learning Work steps
More Deep Learning, AI and Natural Language Processing resources
About deep learning, ai and natural language processing mind maps
GoConqr OriginalDeep Learning, AI and Natural Language Processing mind maps
These maps offer different ways into the unit. The Machine Learning maps include branches on supervised, unsupervised and reinforcement learning. Deep Learning maps cover topics such as neural networks, training and optimisation. Other maps focus on models, including DCGAN and Variational Auto-Encoder (VAE).
How to use the maps
For a starting point, try a Machine Learning map that separates the learning types. Its branches give you a structure for exploring methods such as classification and clustering. Then use Word Embeddings to look at how words and documents can be represented in vector space.
For language tasks, eScience Neural NLP includes branches on sentiment analysis and machine translation. Read a branch, then try to recall its main points before checking the map again. If you want to test your recall in another format, switch to flashcards or a quiz on the unit page. Choose a map to start exploring.
Frequently asked questions
Which mind map is a useful place to start?
A Machine Learning map is a useful starting point if you want an overview of learning types. The page has several maps with that title, including one with branches on supervised, unsupervised and reinforcement learning, as well as classification, regression and clustering.
Are these mind maps free to use?
Yes. Every mind map listed here is free to open and study, and you do not need an account. The resources were made by GoConqr users. A free account also lets you make your own mind maps, flashcards, notes and quizzes, and save quiz scores.
What language-processing topics do the maps cover?
The maps include language tasks, word embeddings and text features. eScience Neural NLP has branches on semantic role labelling, sentiment analysis and machine translation. There are also maps on tokenisation and on lexical, syntactic and semantic features, so you can focus on a particular part of the unit.