Videos
Authorship Attribution
Authorship attribution, the science of inferring characteristics of the author from the characteristics of documents written by that author, is a problem with a long history and a wide range of application.
Presenters: Mahla Daneshvar
Video language: Persian (Farsi)
Download from google drive: Here
Big Data Mining
Big data mining is referred to the collective data mining or extraction techniques that are performed on large sets /volume of data or the big data. Big data mining is primarily done to extract and retrieve desired information or pattern from humongous quantity of data.
Presenters: Maryam Barani
Video language: Persian (Farsi)
Download from google drive: Here
Biomedical Question Answering Systems
Biomedical question answering (QA) is a sub-task of natural language processing in a specific domain, which aims to answer a question in the biomedical field based on one or more related passages and can provide people with accurate healthcare-related information.
Presenters: Azadeh Givchi
Video language: Persian (Farsi)
Download from google drive: Here
Deep Learning (Part 1-Neural Networks)
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling.
Presenters: Mahdi Kiani
Video language: Persian (Farsi)
Download from google drive: Here
Deep Learning (Part 2-Neural Networks)
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling.
Presenters: Mahdi Kiani
Video language: Persian (Farsi)
Download from google drive: Here
Deep Learning (Part 3-DL Models)
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling.
Presenters: Mahdi Kiani
Video language: Persian (Farsi)
Download from google drive: Here
Deep Learning
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling.
Presenters: Noorollah Karimtabar
Video language: Persian (Farsi)
Download from google drive: Here
Evolutionary Data Mining
Evolutionary algorithms for data mining work by creating a series of random rules to be checked against a training dataset. The rules which most closely fit the data are selected and are mutated. The process is iterated many times and eventually, a rule will arise that approaches 100% similarity with the training data.
Presenters: Peyman Arebi
Video language: Persian (Farsi)
Download from google drive: Here
Fuzzy Clustering
Fuzzy clustering is a form of clustering in which each data point can belong to more than one cluster. Clustering or cluster analysis involves assigning data points to clusters such that items in the same cluster are as similar as possible, while items belonging to different clusters are as dissimilar as possible.
Presenters: Sajad Manteghi
Video language: Persian (Farsi)
Download from google drive: Here
Introduction to Deep Learning
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling.
Presenters: Ali Aji
Video language: Persian (Farsi)
Download from google drive: Here
Low-resource NLP
Low-resource languages are those that have relatively less data available for training conversational AI systems. In contrast, English, Chinese, Spanish, French, Japanese and more of the European and Western languages are high-resource.
Presenters: Faezeh Khorshidi
Video language: Persian (Farsi)
Download from google drive: Here
Machine Learning with Graphs
Complex data can be represented as a graph of relationships between objects. Such networks are a fundamental tool for modeling social, technological, and biological systems. This topic focuses on the computational, algorithmic, and modeling challenges specific to the analysis of massive graphs.
Presenters: Amir Sartipi
Video language: Persian (Farsi)
Download from google drive: Here
Machine Reading Comprehension
MRC (Machine Reading Comprehension) scans documents and extracts meaning from the text, just like a human reader. You can ask MRC questions about a document and it will use different parts of the content until an answer is formed.
Presenters: Narges Asadi
Video language: Persian (Farsi)
Download from google drive: Here
Machine Reading Comprehension
MRC (Machine Reading Comprehension) scans documents and extracts meaning from the text, just like a human reader. You can ask MRC questions about a document and it will use different parts of the content until an answer is formed.
Presenters: Farnoosh Talebi
Video language: Persian (Farsi)
Download from google drive: Here
Machine Translation
Machine translation, sometimes referred to by the abbreviation MT, is a sub-field of computational linguistics that investigates the use of software to translate text or speech from one language to another.
Presenters: MohammadAli Asgarani
Video language: Persian (Farsi)
Download from google drive: Here
Neural Machine Translation
Neural machine translation is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.
Presenters: Alireza Akhavan Safaei
Video language: Persian (Farsi)
Download from google drive: Here
Opinion Mining and Sentiment Analysis
Sentiment analysis, also referred to as Opinion Mining is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information.
Presenters: Fatemeh Momeni
Video language: Persian (Farsi)
Download from google drive: Here
Opinion Mining
Sentiment analysis, also referred to as Opinion Mining is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information.
Presenters: Farzaneh Taheri
Video language: Persian (Farsi)
Download from google drive: Here
Question Answering
Question answering is a computer science discipline within the fields of information retrieval and natural language processing, which is concerned with building systems that automatically answer questions posed by humans in a natural language.
Presenters: Ameneh Rahimi
Video language: Persian (Farsi)
Download from google drive: Here
Question Answering ( Over Text and Knowledge Base)
Question answering is a computer science discipline within the fields of information retrieval and natural language processing, which is concerned with building systems that automatically answer questions posed by humans in a natural language.
Presenters: Mahnaz Tohidimehr
Video language: Persian (Farsi)
Download from google drive: Here
Question Classification
The aim of question classification is to identify the type of questions and based on question type the expected answer will be extracted from the data. In the past years, question classification was done by using only rule-based approach.
Presenters: Fariba Khazaei
Video language: Persian (Farsi)
Download from google drive: Here
Recommender Systems
A recommender system, or a recommendation system, is a subclass of information filtering system that provide suggestions for items that are most pertinent to a particular user.
Presenters: Reza Shafilou
Video language: Persian (Farsi)
Download from google drive: Here
Social Networks
A social network graph is a graph where the nodes represent people and the lines between nodes, called edges, represent social connections between them, such as friendship or working together on a project. These graphs can be either undirected or directed.
Presenters: Faezeh Negaresh
Video language: Persian (Farsi)
Download from google drive: Here
Text Summarization
text summarization (Automatic summarization in fact) is the process of shortening a set of data computationally, to create a subset (a summary) that represents the most important or relevant information within the original content.
Presenters: Negin Shams
Video language: Persian (Farsi)
Download from google drive: Here
Text Summarization (Abstractive Summarization in QA Systems)
Abstractive summarization is the technique of generating a summary of a text from its main ideas, not by copying verbatim most salient sentences from text. This is an important and challenge task in natural language processing.
Presenters: Sepideh Saleh
Video language: Persian (Farsi)
Download from google drive: Here
Transfer Learning and Finetuning
Transfer learning is an optimization that allows rapid progress or improved performance when modeling the second task.
fine-tuning is the process in which a model’s parameters must be adjusted precisely to fit certain observations.
Presenters: Noorollah Karimtabar
Video language: Persian (Farsi)
Download from google drive: Here
Transfer Learning, Multi-task Learning, Fine-tuning, Zero-shot Learning
Multi-task learning (MTL) is a subfield of machine learning in which multiple learning tasks are solved at the same time, while exploiting commonalities and differences across tasks.
Zero-shot learning (ZSL) is a problem setup in machine learning, where at test time, a learner observes samples from classes, which were not observed during training, and needs to predict the class that they belong to.
Presenters: Zolfa Shefreie
Video language: Persian (Farsi)
Download from google drive: Here
Transformer and Attention Mechanism
A transformer is a deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data.
Attention is a technique that mimics cognitive attention. The effect enhances some parts of the input data while diminishing other parts. the motivation being that the network should devote more focus to the small, but important, parts of the data.
Presenters: Sara Moeini
Video language: Persian (Farsi)
Download from google drive: Here
Visual Question Answering
Visual Question Answering (VQA) is a computer vision task where a system is given a text-based question about an image, and it must infer the answer. Questions can be arbitrary and they encompass many sub-problems in computer vision.
Presenters: Atiye Nikbakht
Video language: Persian (Farsi)
Download from google drive: Here
Web Mining
Web mining is the process of using data mining techniques and algorithms to extract information directly from the Web by extracting it from Web documents and services, Web content, hyperlinks and server logs.
Presenters: Hamideh Gharakhani
Video language: Persian (Farsi)
Download from google drive: Here
Word Embedding Techniques
In natural language processing, word embedding is a term used for the representation of words for text analysis, typically in the form of a real-valued vector that encodes the meaning of the word such that the words that are closer in the vector space are expected to be similar in meaning.
Presenters: Ehsan Garfirouzjaei
Video language: Persian (Farsi)
Download from google drive: Here
Word Embedding Techniques
In natural language processing, word embedding is a term used for the representation of words for text analysis, typically in the form of a real-valued vector that encodes the meaning of the word such that the words that are closer in the vector space are expected to be similar in meaning.
Presenters: Maede Amooshahi
Video language: Persian (Farsi)
Download from google drive: Here