Chuyển đến nội dung chính

Bài đăng

Hiển thị các bài đăng có nhãn AI

[AI] I’ve obtained a new certification: Certified Artificial Intelligence Engineer (CAIE™)

  I’m happy to share that I’ve obtained a new certification: Certified Artificial Intelligence Engineer (CAIE™) from United States Artificial Intelligence Institute one of leading AI organization over the world! 📚 📖

[AI] Artificial Intelligence Overview

Artificial Intelligence Overview  - Supervised Learning  - UnSupervised Learning  - Reinforced Learning  - Overfit Problem  - Natural Language Processing (NLP)  - Computer Vision

[AI] Reinforcement learning: Find Optimal Policy

Two method to find optimal policy 👉 Model Dynamic 👉 Model Free 

[AI] Fundamental concepts of Reinforcement Learning

Agent : The agent is the software program that learns to make intelligent decisions, such as a software program that plays chess intelligently. Environment : The environment is the world of the agent. If we continue with the chess example, a chessboard is the environment where the agent plays chess. State : A state is a position or a moment in the environment that the agent can be in. For example, all the positions on the chessboard are called states. Action : The agent interacts with the environment by performing an action and moves from one state to another, for example, moves made by chessmen are actions. Reward : A reward is a numerical value that the agent receives based on its action. Consider a reward as a point. For instance, an agent receives +1 point (reward) for a good action and -1 point (reward) for a bad action. Action space: The set of all possible actions in the environment is called the action space. The action space is called a discrete action space when our action...

[AI] Generative Adversarial Networks (GANs)

 Generative Adversarial Networks (GANs):  - Type of deep neural network architecture that uses unsupervised machine learning - Made up by generator and a discriminator network. Both networks train each other, while simultaneously trying to outwit each other. Generator network - Generate new data  from a randomly generated vector of numbers, called a latent space.  Discriminator network - Tries to differentiate between the real data and the data generated. - It can either perform multi-class classification or binary classification. Important concepts related to GANs - Important measure quality of the models use divergence (KL divergence,  JS divergence...). - Nash equilibrium, which is a state that we try to achieve during training. - Objective functions: To measure the similarity. - Scoring algorithms: Calculating the accuracy of a GAN is simple. Some scoring algorithms: some scoring algorithms, some scoring algorithms,  Mode Score... Problems with traini...

[AI] Text Data Analysis methologys

Text Data Analysis methologys 1. Tokenization Process of dividing text into a set of meaningful pieces. There are three methods of the nltk.tokenize: Sentence-tokenized, Word_tokenize and WordPunctTokenizer. 2. Stemming Word can appear in various forms, reduce these different forms into a common base form. Three stemmer: PorterStemmer, LancasterStemmer, and SnowballStemmer. The LANCASTER is the strictest.  3. Lemmatization:  Reduce words to their base forms but more structured approach. 4. Chunking Divide the input text into pieces with no constraints, chunks do not need to be meaningful at all.  5. Bag-of-words model Dealing with text documents that consist of millions of words, converting them into numerical representations which usable for machine learning algorithms. Models each document by building a histogram of all of the words. Counts the number of occurrences of each word in the document use scikit-learn, represent documents by ignoring the word order.  ...

[AI] Two Methology convert text data into data structure in NLP

2 Methology convert text data into data structure (vector and matrix) 👉  Bag of Word (BoW): Evaluation the frequency of the words in that particular document. Sentence can be represented as a vector with length would be equal to the size of vocabulary. CountVectorizer is python libarary conveniently help in building BoW model. Limitations of the BoW: work well for certain tasks or use cases with a limited vocabulary, not scale to large vocabularies efficiently. 👉  TF-IDF vectors: Approach with weigh terms, vectorizing text and extracting features out of it. TF : account how frequently a term occurs in a document. IDF : justice to terms that occur not so frequently across documents. TF-IDF is computationally fast however does not take into account co-occurrence of terms, semantics, the context associated with terms. Both method use Cosine to evaluation how similar or dissimilar text documents. 

[AI] Interesting Deep Learning Algorithms

4  Interesting Deep Learning Algorithms 1. Artificial Neural Networks (ANNs) 👉 With 3 Layers - Input layer : No computation is performed,  just used for passing information from the outside to the network. - Hidden layer : Deriving complex relationships between input and output. Identifies the pattern in the dataset, learning the data representation and for extracting the features. We cloud use many hidden layers, each layer is responsible for extracting important features. - Output layer:  Number of neurons in the output layer is based on the type of problem we want our network to solve (Example: binary classification, number of neurons in the output layer is one).  ⏩ Other Concept: - Activation functions ( ex: sigmoid, tanh, ReLU, softmax ): To introduce a non-linear transformation to learn the complex underlying patterns in the data. - Cost function:  Use Optimization Algorithms (Gradient descent) to minimize cost so that Network predictions will b...

[AI] Avoid AI Data Model Overfit

Methology for avoid AI Data Model Overfit

[AI] The three V’s of Big Data

3 V’s of big data Volume : Challenge will just keep on getting bigger. Currently Facebook has more users than China has people. 👀 Velocity : How fast data coming in. Facebook was received 735M comments/421M status/195M image uploads per days... ten year ago. 💨💨💨 Variety : Almost of data is unstructured (storing photographs, sensor data, IoT device information, tweets, encrypted packets, voice, video...). 👻

[AI] Big Tech Cloud AI service

Cloud AI service from AWS, GCP and Microsoft Azure.

[AI] How to create model with CRISP-DM modeling approach

6 step to created AI model by  CRISP-DM modeling approach 📚📚 1. Business Understanding : defining business objectives, clarify the queries related to core business objectives.  2. Data understanding : about historical data. 3. Data preparation : raise quality data to level required for machine learning algorithms could be process it.  4. Modeling : selecting a modeling technique or algorithm 5. Evaluation : assessing the accuracy. 6. Deployment : strategy for the training model in the live environment to work on new data. The models are monitored for accuracy. CRISP-DM (cross-industry standard process for data mining) 

[AI] BÀI 05: Các thuật toán tìm kiếm phổ biến

1.  Brute-Force Search Strategies Đây là thuật toán đơn giản nhất, nó không yêu cầu nhiều kiến thức chuyên nghành. Phù hợp cho việc tìm kiếm trong phạm vi số lượng state nhỏ. Nó yêu cầu: State description A set of valid operators Initial state Goal state description Có 05 cách để thực hiện chiến lược search brute force, bảng so sánh các cách tìm kiếm theo chiến lược này: Criterion Breadth First Depth First Bidirectional Uniform Cost Interactive Deepening Time b d b m b d/2 b d b d Space b d b m b d/2 b d b d Optimality Yes No Yes Yes Yes Completeness Yes No Yes Yes Yes 2.  Informed (Heuristic) Search Strategies Ứng dụng trong việc tìm kiếm ở môi trường có số lượng state lớn. Nó yêu cầu kiến thức chuyên ngành để tăng hiệu quả của việc tìm kiếm. Có bốn phương pháp thực hiện chiến lược tìm kiếm này Heuristic Evaluation Functions Pure Heuristic Search A * Search Greedy Best First Search 3.  Local Search Algorithms Bắt đầu từ một giải pháp tiềm...

[AI] BÀI 4: Tác nhân và môi trường (Agent and Environment)

1. Agent (tác nhân): l à tất cả những gì có thể nhận thức về môi trường của nó thông qua cảm nhận "Sensor" và đưa ra hành động tác động đến môi trường (effective). Có 03 loại agent: human, software, robotic. + Cấu trúc của Agent: Gồm 2 phần:  Architecture + Agent Program + Phân loại Agent: -  Simple Reflex Agents: Agent phản ứng đơn giản. - Model Based Reflex Agents: Agent phản xạ dựa trên model - Goal Based Agents: Agent dựa trên mục tiêu. - Utility Based Agents: Agent dựa trên tính tiện ích. 2. Turing test : Ứng dụng trong việc kiểm tra và đáng giá máy móc có thật sự thông minh?  https://vi.wikipedia.org/wiki/Ph%C3%A9p_th%E1%BB%AD_Turing   3. Các thuộc tính của môi trường Discrete / Continuous  − If there are a limited number of distinct, clearly defined, states of the environment, the environment is discrete (For example, chess); otherwise it is continuous (For example, driving). Observable / Partially Observable  ...

[AI] BÀI 3: Các lĩnh vực ứng dụng và phân loại công việc của AI

1. Các lĩnh vực ứng dụng của AI Sr.No. Research Areas Real Life Application 1 Expert Systems Examples − Flight-tracking systems, Clinical systems. 2 Natural Language Processing Examples: Google Now feature, speech recognition, Automatic voice output. 3 Neural Networks Examples − Pattern recognition systems such as face recognition, character recognition, handwriting recognition. 4 Robotics Examples − Industrial robots for moving, spraying, painting, precision checking, drilling, cleaning, coating, carving, etc. 5 Fuzzy Logic Systems Examples − Consumer electronics, automobiles, etc. 2. Phân loại công việc của AI Các công việc của AI được phân thành 03 loại công việc : - Mundane tasks:  Nhóm những công việc thuộc về bản năng thông thương: nói, nhìn, viết chữ... - Formal tasks: Những công việc có tính quy tắc như Toán học, địa lý, Logic... - Expert tasks: Nhóm công việc có tính chuyên gia: Sản xuất, giám sát... Đối với con người ...

[AI] BÀI 2: Sự khác biệt giữa nhận thức của người và máy

1. Nhận thức - Con người nhận thức thông qua các mẫu - parttern. - Máy nhận thức dựa trên data và rule 2. Truy vấn thông tin - Con người: truy vấn thông qua partter. - Máy: truy vấn thông qua thuật toán. 3. Khả năng hiểu về đối tượng : - Con người: có thể hiểu hoàn toàn về một đối tượng cho dù một vài thông tin của đối tượng bị thiếu hoặc nhiễu.  - Máy: Không thể hiểu một cách chính xác. 

[AI] BÀI 1: Khái niệm cơ bản về trí tuệ (intelligent) và học tập (learning)

1. Trí thông minh - intelligent là gì? Dùng để chỉ khả năng của một hệ thống để tính toán, lý luận, nhận thức quan hệ và phân tích, học từ trải nghiệm, lưu trữ và retreive thông tin từ bộ nhớ, giải quyết vấn đề, ra quyết định ... 2. Các loại trí thông minh : Có 07 loại trí thông minh  Intelligence Description Example Linguistic intelligence The ability to speak, recognize, and use mechanisms of phonology (speech sounds), syntax (grammar), and semantics (meaning). Narrators, Orators Musical intelligence The ability to create, communicate with, and understand meanings made of sound, understanding of pitch, rhythm. Musicians, Singers, Composers Logical-mathematical intelligence The ability of use and understand relationships in the absence of action or objects. Understanding complex and abstract ideas. Mathematicians, Scientists Spatial intelligence The ability to perceive visual or spatial information, change it, and re-create visual images without reference to the objects, ...