Transcript: machine learning The majority of AI experts think AI will be able to accomplish any intellectual task humans can perform by 2050. what is machine learning? WHAT definition Machine learning is a field of computer science that gives computer systems the ability to "learn" with data, without being explicitly programmed. what is the Difference between Ai,machine learning and deep learning ? we are familiar with AI(Artificial Intelligence) but recently we are hearing about "Machine Learning" and "Deep Learning" sometime used interchangeably with AI. As a result their difference become unclear. Artificial intelligence(ai) ai First coined in 1956 by John McCarthy, AI involves machines that can perform tasks that are characteristic of human intelligence like understanding languages,recognizing object and sound,learning,problem solving etc. There are two categories of AI: General AI: It consist of all characteristics of human intelligence. Narrow AI: It exhibits some facets of human intelligence and is extremely good at it. Artificial intelligence machine learning Machine Learning is a way of achieving AI. “The ability to learn without being explicitly programmed” is Machine Learning. We can get AI without using machine learning, but this would require building millions of lines of codes with complex rules and decision-trees. machine learning Deep Learning Deep learning is one of many approaches to machine learning. Other approach includes decision tree learning,Support vector Machine(SVM), Random Forest etc. Deep learning was inspired by the structure and function of the brain, namely the interconnecting of many neurons. Artificial Neural Networks (ANNs) are algorithms that mimic the biological structure of the brain. deep learning deep learning architecture comparison how machine learning work? Working of machine learning depends on its type. Types supervised learning supervised learning supervised Learning contain input variables and output variables. In supervised learning we uses machine learning algorithms to learn the mapping function from input to output variables. There are two types of problems in supervised learning: Classification Problem - Try to learn the the category of the class. Regression Problem - Try to learn the real value of the class. unsupervised learning unsupervised learning In unsupervised Learning there is no right or wrong answer.we have input data points . we try to learn information about the data points. There two types of Problems : Clustering - Try to learn group in which data points belong to. Association - Try to learn the rule which better explain the data points. reinforcement learning reinforcement learning Using this algorithm, the machine is trained to make specific decisions. It works this way: the machine is exposed to an environment where it trains itself continually using trial and error. The machine learns from past experience and tries to capture the best possible knowledge to make accurate business decisions Algorithm for each types Algkorithms for each type Different machine learning algorithms In machine learning there's something called "No free Lunch" theorem.In a nutshell,it means no one algorithm works for every problem. algo Find here commonly used machine learning algorthms commonly used machine learning algorthms Linear Regression Logistic Regression Decision Tree SVM Naive Bayes kNN K-Means Random Forest Dimensionality Reduction Algorithms Gradient Boosting algorithms GBM XGBoost LightGBM CatBoost Linear Regression price = room * 100 110 210 310 410 510 610 710 skills required skills Machine Learning Engineer Data Analysis Job Role Data Analysis Machine Learning Life cycle Data Scintest Machine Learning Engineer Skills Skills ML Tools DL Tools Big Data Data Visualization Cloud Technologies Data Science Lifecycle Data Scintest Jobs in Machine Learning job Egypt Salary Saudi Arabia World JOBS Specialization Degress application of machine learning Ml based products and projects ml products Benefit of Machine Learning ml products THANK YOU!! THANK YOU - Osama Mo
Transcript: machine learning The majority of AI experts think AI will be able to accomplish any intellectual task humans can perform by 2050. what is machine learning? WHAT An area of artificial intelligence devoted to algorithms that improve automatically through exposure to data definition what is the Difference between Ai,machine learning and deep learning ? Artificial intelligence(ai) Machines that can perform tasks that are characteristic of human intelligence like: understanding languages recognizing object and sound learning problem solving etc. ai machine learning Machine Learning is a way of achieving AI. machine learning Deep Learning Deep learning is one of many approaches to machine learning. deep learning deep learning architecture how machine learning work? how supervised learning In supervised learning we uses machine learning algorithms to learn the mapping function from input to output variables. There are two types of problems in supervised learning: Classification Problem - Try to learn the the category of the class. Regression Problem - Try to learn the real value of the class. supervised learning unsupervised learning In unsupervised Learning there is no right or wrong answer. We try to learn information from the data. There two types of Problems : Clustering - Try to learn group in which data points belong to. Association - Try to learn the rule which better explain the data points. unsupervised learning reinforcement learning The machine is exposed to an environment where it trains itself continually using trial and error. The machine learns from past experience and tries to capture the best possible knowledge to make accurate business decisions reinforcement learning WHY Why machine learning is important ? Machine learning has enhanced our ability to perform almost every intellect task by replacing or significantly augmenting older approaches. Different machine learning algorithms algo commonly used machine learning algorthms Linear Regression Logistic Regression Decision Tree SVM Naive Bayes kNN K-Means Random Forest Dimensionality Reduction Algorithms Gradient Boosting algorithms GBM XGBoost LightGBM CatBoost skills required in machine learning Understanding the fundamentals of statistics, optimization, and building quantitative models Knowing programming proficiency and understand the basics of system design Working with large data sets Understanding programing languages as Python, R or C/C++ skills THANK YOU!! THANK YOU Szymon Deczkowski Adrian Kruczyński Sources we used 3Blue1Brown: https://www.youtube.com/watch?v=aircAruvnKk Simplilearn: https://www.youtube.com/watch?v=-DEL6SVRPw0&t Wikipedia: https://en.wikipedia.org/wiki/Machine_learning Sources
Transcript: Brenden Schumacher Public Speaking 23 April 2020 Machine Learning Reality TODAY, AI LOOKS MORE LIKE THIS Machine Learning Reinforcement TODAY WHERE ARE WE TODAY? THE GOOD THE BAD STILL LEARNING FUTURE ON THE VERGE IN HEALTHCARE AT HOME GROWTH
Transcript: machine learning Student: Kairgali Zhanar what is machine learning? WHAT definition Machine learning is a field of computer science that gives computer systems the ability to "learn" with data, without being explicitly programmed. types what are the types of machine learning? types of machine learning find here Supervised Learning Unsupervised Learning Reinforcement learning Machine Learning in accounting and Auditing Фml&acc find here Machine learning, gave rise to different ways of accomplishing tasks, which also affected the accountancy and auditing professions. Despite the drawbacks, implementing machine learning tools has many advantages: Increased efficiency Effectiveness by faster data analysis High-quality audit Error reduction Early identification of risks Creating a competitive advantage THANK YOU THANK YOU!!
Transcript: Machine Learning Tejveer, Faizan, Fahim, Amanjot What is Machine Learning? What is Machine Learning Machine learning is the process of algorithms that can self improve automatically through experience and using data. How Machine Learning Works How machine learning works Decision Process Error Function Model Optimization Process Supervised machine learning Unsupervised machine learning Semi-supervised learning Machine learning methods History of Machine Learning 1950 - Turing Test 1952 - Arthur Samuel's Game 1957 - Frank Rosenblatt's perceptron 1967 - Nearest Neighbor 1979 - Stanford's Cart 1985 - NetTalk 1997 - IBM's Deep Blue 1999 - University of Chicago creates cancer computer 2006 - Geoffrey Hinton coins term Deep Learning (Lead to present day) History Movies and Machine Learning Movies and Machine Learning - Throughout history, tech seen on movies helped shape today's - Metropolis by Fritz Lang - 2001 by Kubrick - Blade Runner Why is it Important in the Present? Why is it important in the present Importance of collecting data for future Various uses worldwide in different systems System Examples Speech Recognition Car self driving feature Facial Recognition General Medicine Many more examples! Machine Learning in 10 Years Where Will This Technology be in 10 Years? - Machine learning will be implemented almost anywhere - Pharmacies will implement machine learning - Prediction of diseases, discovery of drugs, and electronic health records - Car companies are already implementing machine learning in self driving cars Quantum Computing How Quantum Computing will Effect the Future of Computer Learning What is quantum computing? How will it effect machine learning? How much more better is quantum computing? How will machine learning effect the economy in the future? Economy - Market predicted to rise from 8.43 billion to around 117.19 billion - Will be implemented in self driving cars and the pharmaceutical market - Car & pharmaceutical market will increase which will cause economy to increase
Transcript: Hypothesis What is Cellobiose? Mechanism of hydrolysis What is Mushroom? What we get in previous experiment Hypothesis We got standard curve! if pH get lower, the reaction rate increase! if temperature increase, the reaction rate increase Contents Group 2 김경한, 김규식, 유혁준, 정지우, 양윤후 Our research plan What we get in the experiment The handle part of the mushroom's enzyme concentration will be higher than cap part Mushroom Cellobiose is a carbohydrate that contains 2 glucoses with glycoside bond. y intercept Spore-breeding Fungi Some kind of it can be edible Has enzyme to hydrolize cellobiose Hydrolysis slope Our research plan Cellobiose seperate cap and handle part of mushroom extract enzyme compare reaction rate & pH and temperature Glycoside bond You can't eat this!!!
Transcript: Machine Learning What is Machine Learning What is Machine Learning? “Machine Learning is a field of computer science that applies statistical techniques to give the system the ability to “learn”.” (from Wiki) The model “learns” from those data points. → if you the model knows x, it will predict y. Example Define Project Objective Define Project Objectives Specify business problem Acquire subject matter expertise Define unit of analysis and prediction target, find and remove any target leakage Prioritize modeling criteria Consider risks and success criteria Decide whether to continue Acquire & Find Appropriate Data Acquire & find appropriate data 1. Find appropriate data 2. Merge data into single table 3. Conduct exploratory data analysis 4. Feature engineering Find Appropriate Data Source: internal, external, public Step 1 & 2 Merge Data Source engineering and BI team Step 3 View Raw Data: missing, wrong content (table importing), strange data input Study Distribution of each Variable/Column Plots Single variable Discrete: bar chart, box-plot, etc. Continuous: histogram etc. Multiple variables → scatter plots Study Descriptive statistics: min, max, mean, variance, median for each variable Conduct Exploratory Data Analysis Bar Chart is NOT the same as histogram at all Step 4 Feature: column/field/variable Feature Engineering: create feature to make machine learning work Also known as data transformation Numeric skewed data → normally distributed to meet model requirements Non-linear relationship between X and Y → linear relationship between them for modeling Refill missing values Differences of features (time-series data) Categorical Categorize variables for modeling (classification model) Text For comments analysis: sentimental analysis etc. Date Day difference Feature Engineering Model Data Model Data Variable selection Build candidate models Model validation and selection Linear Regression Linear Regression Limitation of Linear & Logistic Regression Limitation of LR Decision Trees Decision Trees Over vs Under Fitting Over vs Under Fitting Cross Validation Cross Validation Interpret Model Interpret & Communicate Model Can we believe the model in practice? Unlock holdout dataset after we decide model Measure model performance again Confusion Matrix Lift Chart ROC Curve Others: model performance vs sample size; model speed vs model accuracy etc. Communicate Depends on audiences Management Team: Top Level (effects, impacts etc.) Data Team: Very detailed information (models, parameters, etc.) Confusion Matrix Often used for measuring accuracy of classification models Pro: interpret friendly (easy to map business concepts) Con: imprecise Conclusion: quick view of our model performance Confusion Matrix Lift Chart Pros: Straightforward Accuracy prediction & model’s overall behavior Cons: Tend to focus on prediction only Lift Chart ROC Curve Pro: Precise measure of model’s performance Cons: Not easy interpretation Rank ordered probability only Compare models ROC (Receiver Operating Characteristic) Curve New vs Old Data New vs Old Data Set target column of old data as one Run model with old data only Predict target column of combined data using existing model coefficients Exam performance metrics of new target column Auto-Document all modeling steps Documentation Document Demo w. real data
Description: Impactful presentations need stunning visuals and a meaningful metaphor to show high-level concepts and the smaller details. This customizable presentation template uses a classic world map visual to help you navigate complex information while staying grounded in your presentation’s core message.
Description: Rise way above the stacks and stacks of two-dimensional paper resumes on the hiring manager’s desk with a Prezi resume template. Simply personalize this Prezi presentation template to create your very own “Prezume” and impress them with your dynamism, originality, and cool.
Description: For grant requests, program proposals, or any other nonprofit or education presentation, this globe-themed creative Prezi template is the way to generate interest and momentum. Like all Prezi education templates and Prezi nonprofit templates, it’s easy to customize.
Now you can make any subject more engaging and memorable