Machine Learning

Get Started. It's Free
or sign up with your email address
Machine Learning by Mind Map: Machine Learning

1. Algorithms

1.1. Deep Boltzman Machine (DBM)

1.2. Deep Belief Network (DBN)

1.3. Convolutional Neural Networks

1.4. Stacked Auto Encoders

1.5. Hierarachical Temporal Memory

2. Deep Learning

2.1. Definition

2.1.1. Deep Learning is an algorithm which has no theoretical limitations of what it can learn; the more data you give and the more computational time you provide, the better it is. (Geoffrey Hinton)

2.2. Domains

2.2.1. Image Faces Machine vision

2.2.2. Sound Speech to text Machine translation

2.2.3. Text Search Information retrieval

2.2.4. Time Series Weather Biodata Stocks

2.3. Why

2.3.1. CIO looking for highest performance in ML

2.3.2. Advance the state of the art in pattern recognition and natural language processing attempts to model high-level abstractions in data

2.4. Differences

2.4.1. "Normal" neural networks usually have one to two hidden layers and are used for SUPERVISED prediction or classification.

2.4.2. SVMs are typically used for binary classification, but occasionally for other SUPERVISED learning tasks.

2.4.3. Deep learning neural network architectures differ from "normal" neural networks because they have more hidden layers. Deep learning networks differ from "normal" neural networks and SVMs because they can be trained in an UNSUPERVISED or SUPERVISED manner for both UNSUPERVISED and SUPERVISED learning tasks

2.5. Data Scientist seek to process huge amount of unstructured data

3. Definition

3.1. computers learning to predict from data

3.1.1. learning implies improvement through gaining experience or knowledge

3.2. A (machine learning) computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E. (Tom Mitchell)

4. Applications

4.1. Natural Langauge Processing

4.1.1. deep LSTM (long short-term memory)

4.2. Syntactic Pattern Recognition

4.3. Search Engines

4.3.1. from lexical matching (matching terms) to latent semantic analysis (semantic matching) to deep neural network to extract high-level semantic representations

4.4. Medical Diagonsis

4.5. Detection Credit Card fraud

4.6. Stock Market Analysis

4.7. Classifying DNA Sequence

4.8. Speech & handwriting sequences

4.9. Object Recognition in Computer Vision

4.10. Game Playing

4.11. Robot Locomotion

4.12. Multimedia Signal Processing

4.12.1. Image

4.12.2. Speech and Audio

5. Why M.L ?

5.1. because we need to make machines ....

5.1.1. think like humans

5.1.2. notice similarties betwen things and generate new ideas

5.1.3. learn from mistakes

5.1.4. give explanation why things went wrong

5.1.5. Solve problems difficult or impossible for human to solve problems Phenomena are changing rapidly Application need to be customized for each user separately No human experts experts unable to explain thier experience

6. Learning Paradigms

6.1. Supervised

6.1.1. Regression Learning Algorithm Non Parametric Parametric

6.1.2. Classification Fitting Models Linear Regression Logistic Regression Multi i/p case 2- dimension 3- dimension ... infinite dimension

6.2. Unsupervised

6.2.1. Clustring examples Image Processing Organizing computer Clusters Social Network Analysis Market Segmentation Astronomical data analysis Understanding genes data

6.3. ReInforcement

6.3.1. Applied to Web-Crawling Robotics teaching Robot to get over obstcales teaching Car drive off road and avoiding obstacles robotic snake 4-legged robotic dog

6.3.2. idea Reward function

7. Learning Resources

7.1. Deeplearning

7.1.1. first commercial-grade, open-source, distributed deep-learning library written for Java and Scala

7.1.2. Integrated with Hadoop and Spark, Deeplearning4j is designed for business environments and includes a distributed multithreaded deep-learning framework and a single-threaded deep-learning framework

8. Keywords

8.1. Machine only understand numbers. It starts with obvious things and extends to subtle things

8.2. Feature engineering

8.2.1. Finding connections between variables and packing them into a new discreet variable

8.3. The Power to Predict Who Will Click, Buy, Lie, or Die. [Predictive Analytics is) technology that learns from experience [i.e. data] to predict the future behavior of individuals in order to drive better decisions

8.4. Pairing human workers with machine learning and automation will transform knowledge work and unleash new levels of human productivity and creativity

9. Practical Applications

9.1. Shopping Recommendation

9.1.1. better sales automation, lead generation, efficient marketing, predictive hiring, algorithmic trading

9.2. Churn Prediction

9.3. Face tagging

9.4. Sentiment Analysis

9.4.1. Understand emotions regardless of language written

9.5. Youtube uses a deep neural network model to generate higher-quality thumbnails for videos

9.6. Skype real-time translation

9.7. Video monitoring to identify interesting objects such as dogs and trucks

9.8. Google Translate, Voice, Photos. Google driverless car predict appropriate driving actions

9.9. Numenta's Grok predict future energy requirements and prices

9.10. LinkedIn predicts who you want to connect with

10. Future Applications

10.1. Medical imaging

10.1.1. simple chip utilizing cloud computing and deep learning models

10.2. Baidu Deep Speech

10.2.1. transcribe voice queries in Mandarin

11. Purpose

11.1. Increase Sales Performance

11.1.1. 1) Don’t worry if data isn’t 100% accurate to begin with. As long as it’s directionally correct it will stimulate the right discussions. Data quality will improve naturally with use, feedback, updating, and iterative cleansing. 2) Drive excitement and adoption by making the application simple and engaging for the field, with easy-to-understand, interactive visualizations. 3) Integrate predictive analytics into the visualization and discovery process on a self-service basis so that new insights are intuitively delivered as the underlying data and attributes change. This will keep the insights from the application relevant. 4) Use iterative techniques to design and deliver a working app quickly and then adapt it based on user feedback. 5) Partner with IT through this process so that the users receive the desired self-service and flexibility while leveraging the business intelligence platform to maintain data governance, security, and control

11.2. Increase number of customers

11.2.1. reducing attrition/churn using historical data and look for likelihood of churn

11.2.2. acquiring new customers by lead scoring and optimizing marketing campaigns

11.3. Serve customer better

11.3.1. cross-selling products

11.3.2. optimizing products and pricing by mapping product characterizations to no. of sales

11.3.3. Increasing engagement by observing customer behavior and mapping customer-item pairs to interest indicators

11.4. Serve customer more efficienctly

11.4.1. Predicting demand. Observe high variability for services/products

11.4.2. Automating tasks such as scoring credit applications and insurance claims

11.4.3. Making enterprise apps predictive in prioritize things, use adaptive workflows (route customer support requests to best available person), adapt the interface, set configurations and preferences automatically


12.1. an in-memory platform that runs analytics applications smarter, business processes faster, and data infrastructures simpler

12.2. Predictive Analysis Library (PAL)

12.2.1. Association

12.2.2. Classification To predict a binary answer – i.e. Is this transaction fraudulent or not?

12.2.3. Regression To predict or score an amount that is a non-binary value - i.e. Determining the insurance risk factor this this driver

12.2.4. Cluster To find groups in your dataset – i.e. Who are all the people likely to buy my product today? To predict future values based on previously observed values – How likely are flight cancellations in winter vs. summer months?

12.2.5. Time Series

12.2.6. Probability

12.2.7. Outlier

12.3. Automated Predictive Library (APL)

12.3.1. customers, developers, and partners do not need to be data scientists to use the SAP APL – they simply need to feed the APL what they have and tell it what they need.

12.3.2. Classification, Regression, Clustering, TIme Series, Key Influencers

12.4. SAP Lumira

12.4.1. an agile data discovery tool designed to expedite data preparation and enable data to be presented in a visual, easily digestible form

13. Enterprise

13.1. Security/Fraud

13.1.1. BrightPoint Sentinel automate threat detection and risk analysis

13.2. HR/Recruiting

13.2.1. Textio analyzed job text and outcomes data using listings from tens of thousands of companies

13.2.2. hiQ People Analytics helps employee selection, development and retention by modeling historical data to predict future outcomes

13.3. Sales

13.3.1. Sentient Aware uses visual search to help shoppers quickly find the products they want to buy just like a store associate, connecting the right products to every customer

13.4. Marketing

13.4.1. LiftIgniter improves CTR, engagement and conversion by providing personalization using recommendation in real-time

13.5. Customer Support

13.5.1. Clarabridge collects customer feedback from various sources and provide actionable insights

13.5.2. Quantifind tells what's most important in driving people to buy your products by introducing brand strategy. Explanatory analytics potential replacement for survey-based consumer research, brand health studies, focus groups, strategic consulting engagements, etc.

13.6. Internal Intel

13.6.1. Using the combination of machine learning and crowdsourcing from experts identified by their usage of tables, Alation centralizes the knowledge on data and ensures it’s always up-to-date

13.7. Market Intel

13.7.1. Mattermark mines and crunches public Internet data to provide investors, sales teams and others with search tools and other business intelligence,