AI with python Internship program presntation

This slide deck walks you through the essential tools and techniques for building AI with Python. You’ll get clear, hands-on guidance on data preparation, key machine learning algorithms, neural networks with popular libraries (NumPy, pandas, scikit-learn, TensorFlow/PyTorch), model evaluation, and deployment strategies. Perfect for beginners and intermediate learners who want project-focused, real-world examples and code snippets to level up fast.

1. INTERNSHIP Artificial Intelligence with Python

2. Abbreviations AI  Artificial Intelligence ML  Machine Learning NN  Neural Network IP  Image Processing CNN  Convolution Neural Network DL  Deep Learning DNN  Deep Neural Network ANN  Artificial Neural Network www.evisiontechnoserve.com [email protected]

3. AI (ML) – Human Brain www.evisiontechnoserve.com [email protected]

4. Human Organ – AI Tools Eye  Camera Nose  Sensor Ear  MIC, Microphone Mouth  Speaker Tongue (Taste)  Sensors Hands & Legs  Motors (Robotics) Emotions  Software www.evisiontechnoserve.com [email protected]

5. AI – Basics The father of Artificial Intelligence is John McCarthy . The science and engineering of making intelligent machines, especially intelligent computer programs. Artificial Intelligence is a way of making a computer, a computer-controlled robot, or software think intelligently, in a similar manner the how intelligent humans think. AI is accomplished by studying how the human brain thinks and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis for developing intelligent software and systems.

6. www.evisiontechnoserve.com [email protected]

7. Concepts in AI Machine Learning NLTK Package (Natural Language Toolkit Package) , NLP(Natural Language Processing) Speech Recognition Heuristic Search Gaming Neural Networks Genetic Algorithms Computer Vision Deep Learning Robotics www.evisiontechnoserve.com [email protected]

8. Good Qualities of Human & AI Human is good with emotions, thinking and can perform huge number of activities with the support of all the external organs. Machines  lifting 1000 kg weight (JCB), AI  JCB (Robotics) with camera, emotions (sensors and SW), Speaker to tell about issues. www.evisiontechnoserve.com [email protected]

9. Human - AI AI Goal  to create system which can function Intelligently and Independently. Human Speak &Listen  Speech Recognition Write & Read Text  NLP (Natural Language Processing). See with Eyes, Process, Recognize Computer Vision (Image Processing) Understand & Move freely  Robotics Like & Unlike objects grouping and Patterns  Pattern Recognition (Machine Learning, more data and dimensions of data) www.evisiontechnoserve.com [email protected]

10. Human - AI Brain, Network of Neurons  Neural Network More complex & deeper  Deep Learning or Deep Neural Network

11. Key Points AI  ML, IP, NN, CNN, DS, DL, all these topics are part of AI AI or ML  Data to train the algorithm. www.evisiontechnoserve.com [email protected]

12. IDE - Software Anaconda platform Jupyter Notebook Idle IDE Pycharm www.evisiontechnoserve.com [email protected]

13. Installation of useful packages pip install numpy pip install scipy pip install matplotlib pip install sklearn pip install pandas pip install sys pip install keras pip3 install --upgrade tensorflow www.evisiontechnoserve.com [email protected]

14. Testing of Installed Packages www.evisiontechnoserve.com [email protected]

15. Numpy NumPy is an open-source library available in Python that aids in mathematical, scientific, engineering, and data science programming. Multi-dimensional arrays and matrices multiplication. The library’s name is actually short for "Numeric Python" or "Numerical Python". NumPy is memory efficient, meaning it can handle vast amount of data more accessible than any other library. www.evisiontechnoserve.com [email protected]

16. Tensorflow Developed by Google Open Source The Advantages of Tensor Flow are - It has excellent community support, It is designed to use various backend software (GPUs, ASICs), etc., and also highly parallel, It has a unique approach that allows monitoring the training progress of our models and tracking several metrics, & Its performance is high and matching the best in the industry. There are 4 main tensor types you can create in TensorFlow - tf . Variable, tf.constant , tf.placeholder , & tf.SparseTensor . www.evisiontechnoserve.com [email protected]

17. AI - Types Symbolic Based  Computer Vision, Image Processing, Camera, Video, Image, Robotics. Machine Learning  Based on data. Feed machine with lot of data, so it can learn and perform. (Ex – Lot of data of Sales versus Advertising spent, then ML can learn and draw pattern in more than 100 and 1000 dimensions) ML  Classification & Prediction (Shop Ex – classifying customers as per data (old / new, age) and assign toys, and predict their next interest of purchase) www.evisiontechnoserve.com [email protected]

18. Machine Learning Machine learning  field of computer science, an application of artificial intelligence, which provides computer systems the ability to learn from data and improve from experience without being explicitly programmed. The main focus of machine learning is to allow computers to learn automatically without human intervention. Observations of data  . The data can be some examples, instructions, or direct experiences, too. Then, on the basis of this input, the machine makes a better decision by looking for some patterns in the data. www.evisiontechnoserve.com [email protected]

19. www.evisiontechnoserve.com [email protected]

20. Data Input types Excel Data  Numbers and Strings Images or Videos Audio Signals www.evisiontechnoserve.com [email protected]

21. Types of Machine Learning Algorithms Supervised machine learning algorithms Unsupervised machine learning algorithms Reinforcement machine learning algorithms AI is a combination of complex algorithms from the various mathematical domains such as Algebra, Calculus, Probability, and Statistics. www.evisiontechnoserve.com [email protected]

22. Supervised machine learning algorithms This is the most commonly used machine learning algorithm. It is called supervised because the process of algorithm learning from the training dataset can be thought of as a teacher supervising the learning process. In this kind of ML algorithm, the possible outcomes are already known and training data is also labeled with correct answers. www.evisiontechnoserve.com [email protected]

23. Supervised machine learning algorithms Mainly supervised leaning problems can be divided into the following two kinds of problems − Classification − A problem is called classification problem when we have the categorized output such as “black”, “teaching”, “non-teaching”, etc. (Ex: Classify all types of flowers, Classify Dolphin or Seahorse) Regression − A problem is called regression problem when we have the real value output such as “distance”, “kilogram”, etc. www.evisiontechnoserve.com [email protected]

24. Supervised machine learning algorithms www.evisiontechnoserve.com [email protected]

25. Supervised machine learning algorithms www.evisiontechnoserve.com [email protected]

26. Supervised - Regression Regression is one of the most important statistical and machine learning tools. It may be defined as the parametric technique that allows us to make decisions based upon data or in other words allows us to make predictions based upon data by learning the relationship between input and output variables. Here, the output variables dependent on the input variables, are continuous-valued real numbers. In regression, the relationship between input and output variables matters and it helps us in understanding how the value of the output variable changes with the change of input variable. Regression is frequently used for prediction of prices, economics, variations, and so on. www.evisiontechnoserve.com [email protected]

27. Supervised machine learning algorithms Gaussian naive bayes Support Vector Machines (SVM) Logistic Regression Random Forest Classifier K-Nearest Neighbors (KNN) Classifier www.evisiontechnoserve.com [email protected]

28. Unsupervised machine learning algorithms algorithms do not have any supervisor to provide any sort of guidance. That is why unsupervised machine learning algorithms are closely aligned with what some call true artificial intelligence. Suppose we have input variable x, then there will be no corresponding output variables as there is in supervised learning algorithms. In simple words, we can say that in unsupervised learning there will be no correct answer and no teacher for the guidance. Algorithms help to discover interesting patterns in data. www.evisiontechnoserve.com [email protected]

29. Unsupervised machine learning algorithms Unsupervised learning problems can be divided into the following two kinds of problem − Clustering − In clustering problems, we need to discover the inherent groupings in the data. The main goal of clustering is to group the data on the basis of similarity and dissimilarity. For example, grouping customers by their purchasing behavior. Association − A problem is called association problem because such kinds of problem require discovering the rules that describe large portions of our data. For example, finding the customers who buy both x and y. www.evisiontechnoserve.com [email protected]

30. Unsupervised machine learning algorithms

31. Unsupervised machine learning algorithms

32. Unsupervised machine learning algorithms K-means clustering algorithm Mean Shift clustering Algorithm www.evisiontechnoserve.com [email protected]

33. Reinforcement machine learning algorithms These kinds of machine learning algorithms are used very less. These algorithms train the systems to make specific decisions. Basically, the machine is exposed to an environment where it trains itself continually using the trial and error method. These algorithms learn from past experience and try to capture the best possible knowledge to make accurate decisions. Markov Decision Process is an example of reinforcement machine learning algorithms. www.evisiontechnoserve.com [email protected]

34. www.evisiontechnoserve.com [email protected]

35. www.evisiontechnoserve.com [email protected]

36. Block or Architecture Diagram Laptop python Dataset images / Excel Dataset Algorithm Output display Loan available or not Library opencv , sklearn www.evisiontechnoserve.com [email protected]

37. Methodology Input Image – Real-time Camera / Static Image / Excel Dataset Import Libraries Dataset Visualization processing of the data feature extraction Graphical View output Split Train and Test Data Machine learning Analysis Output Prediction www.evisiontechnoserve.com [email protected]

38. Dataset Analysis Dataset  Columns are called as  Features, Dimensions, Attributes, Variables, Parameters, etc. Balanced or Imbalanced Data. Output  Class or Label Parameters  Check value counts of required parameters (Ex, output) Fill empty cells with the Average value of that parameter. Remove empty Cells. Remove imbalanced data Delete unwanted columns www.evisiontechnoserve.com [email protected]

39. Preprocessing the Data ML requires formatted data to start the training process. We must prepare or format data in a certain way so that it can be supplied as an input to ML algorithms. In our daily life, we deal with lots of data, but this data is in raw form. To provide the data as input to machine learning algorithms, we need to convert it into meaningful data. In other simple words, we can say that before providing the data to the machine learning algorithms, we need to preprocess the data. www.evisiontechnoserve.com [email protected]

40. Preprocessing Steps Importing the useful packages  : import numpy , sklearn , matplotlib, etc. Example Dataset  online, library, or download in Excel CSV format. Binarization  : all the values above 0.5(threshold value) would be converted to 1, and all the values below 0.5 would be converted to 0. Mean Removal Scaling Normalization Labeling the data Train data & Test data www.evisiontechnoserve.com [email protected]

41. Input Image When a computer sees an image, it will see an array of pixel values. Let's say we have a color image in JPG form and its size is 480 x 480. The representative array will be 480 x 480 x 3 array of numbers (The 3 refers to RGB values). Each of these numbers is given a value from 0 to 255 which describes the pixel intensity at that point.

42. Image – Feature Extraction Color – Pixel Intensity Shape Texture www.evisiontechnoserve.com [email protected]

43. How an Algorithm will Process the Image

44. How an Algorithm will Process the Image

45. Image Processing Ex

46. www.evisiontechnoserve.com [email protected]