Modelling Flashcards
What is AI?
AI, refers to any technique that enables computers to mimic human intelligence. An artificially intelligent machine works on algorithms and data fed to it and gives the desired output.
Define ML.
ML enables machines to improve at tasks with experience. The machine here learns from the new data fed to it while testing and uses it for the next iteration. It also takes into account the times when it went wrong and considers the exceptions too.
Define DL.
DL enables software to train itself to perform tasks with vast amounts of data. Since the system has got huge set of data, it is able to train itself with the help of multiple machine learning algorithms working altogether to perform a specific task.
Explain AI as an umbrella terminology.
Artificial Intelligence is the umbrella terminology which covers machine and deep learning under it and Deep Learning comes under Machine Learning.
It is a funnel type approach where there are a lot of applications of AI out of which few are those which come under ML out of which very few go into DL.
Advantages of ML.
- Better decisions and predictions
- Quick and accurate outcomes
- More and powerful processing capacity.
- Analysing complex big data.
- Managing large amounts of data.
- Inexpensive.
Advantages of DL.
- Performance improves with more data.
- Better scalability.
- Problems solved in an end-to-end method.
- Best features are selected by the system.
- Is a subset of Machine Learning.
- Lesser testing time.
Uses of ML.
- Spam detection.
- Search Engine Result Refining.
- Increased efficiency in healthcare.
- Better marketing techniques.
Uses of AI.
- Smart home devices.
- Detecting crimes before they happen.
- Humanoid AI helpers.
Uses of DL.
- Increased Personalization
- Hyper intelligent personal assistants.
Define modelling.
AI Modelling refers to developing algorithms, also called models which can be trained to get intelligent outputs.
- That is, writing codes to make a machine artificially intelligent.
There are two ways of approaching modelling: -
- Learning based approach
- Rule Based approach
Learning Based is classified into: -
- Machine Learning
- Deep Learning
approaches taken by researchers when building AI models
a rule based approach or learning approach.
A Rule based approach is generally based on the data and rules fed to the machine, where the machine reacts accordingly to deliver the desired output.
Learning approach, the machine is fed with data and the desired output to which the machine designs its own algorithm (or set of rules) to match the data to the desired output fed into the machine.
Describe Learning Based Approach
- In this approach , the machine learns through experience. It uses the models and algorithms and perform tasks. These tasks are performed on the sample data which is also known as TRAINING DATA.
- In this programmer need not to tell what to do. The machine is fed with data and it simply compares it with the previous data sets and learns from that.
Describe rule based approach
- This approach is based on data set and rules that are fed into the system to process and gives the result. In this approach, the rules and regulations are already fed into the AI model along with their attributes that is each data is labeled.
- While testing the model with an image , this image is compared with the training data according to the labels of the data.
Difference between two model approaches.
