18CSE483T - INTELLIGENT MACHINING UNIT 4 & 5 - 4M

 4M:

Compare and contrast different Neural Network Architecture

Feedforward NN	Feedback NN	Self-organizing NN
Layers of neurons connected in a forward direction without cycles	Layers can form cycles, allowing feedback loops	Neurons are organized into a lattice structure
Simplicity, ease of implementation	Capturing temporal dependencies, dynamic behavior	Adaptive learning, ability to detect patterns
Suitable for structured data	Suitable for temporal or sequential data	Suitable for clustering and unsupervised learning
Cannot capture temporal dependencies	Complexity in training, potential instability	Lack of supervised training, interpretability challenges
Regression, classification tasks	Time-series prediction, dynamic systems	Pattern recognition, data visualization

Compare and contrast forward propagation and backward propagation

Forward propagation	Backward propagation
Calculate the output of the neural network	Adjust weights to minimize the error
Input data is passed through the network	Gradients are calculated and used to update weights
From input layer to output layer	From output layer to input layer
Activations, weighted sums, and application of activation functions	Gradient of the loss function with respect to weights
Produces the predicted output	Optimizes the network parameters

Elaborate about the Interrupt routines in RTOS

1. Interrupt Latency: 

• Interrupt latency is the time from the arrival of an interrupt to the start of its service by the CPU. 

• RTOS kernels minimize interrupt latency 

2. Interrupt Handling:

• Interrupts can be processed directly in interrupt handlers or as pseudo-tasks with higher priorities than ordinary tasks.

• An efficient RTOS supports nested interrupts, allowing high-priority interrupts to preempt lower-priority ones.

3. Critical Regions:

• RTOS kernels ensure that critical regions are kept as short as possible to reduce the impact on interrupt latency.

4. Preemptive Scheduling:

• RTOS uses preemptive task scheduling, where a higher-priority task can interrupt a lower-priority task at any time.

5. Advanced Task Scheduling Algorithms:

• In addition to preemptive scheduling, RTOS often uses advanced scheduling algorithms(Eg: RMS, EDF) to ensure that all tasks meet their deadlines.

6. Task Management:

• RTOS supports static and dynamic task creation, though static tasks are preferred for better predictability.

Elaborate the memory management system in RTOS

1. Fixed Size Memory Allocation:

• RTOS typically allows tasks to allocate memory in fixed-size blocks rather than arbitrary-sized chunks. 

• This reduces fragmentation and ensures predictability in memory allocation.

2. Avoidance of Virtual Memory:

• RTOS often avoids using virtual address mapping to ensure that memory access times are predictable and meet real-time requirements.

3. Stack Overflow Checking:

• During development, RTOS supports stack overflow checking to ensure that tasks do not exceed their allocated stack space, which can lead to unpredictable behavior and system crashes.

4. Memory Protection:

• In systems with high security and reliability requirements, tasks may run in separate virtual address spaces to prevent one task from accessing the memory of another.

5. Shared Memory:

• RTOS uses shared memory protected by simple mutexes for direct task communication.

6. Memory Management for Task Communication:

• Pipes and synchronous message passing are also used for task communication, where pipes allow tasks to share streams of data and synchronous message passing allows tasks to exchange messages reliably.

Write short note about Fuzzy set membership grade

Fuzzy set theory:

• An extension of classical set theory

• Elements have varying degree of membership

• A logic based on two truth values, true and false

• Fuzzy logic uses the whole interval between 0 (false) and 1 (true) to describe human reasoning

• Membership grade of element is in closed interval [0,1]

• 0 -> non-member

• 1 -> full member

• Between 0-1 -> partial member grade

Write about machining optimization

Objective in machining problem:

• Minimization of cost of machining

• Maximization of production rate

• Maximization of profit rate

Constraints: 

• Constraint on tool life

• Constraints of surface finish

• Constraint on machining process

optimization technology:

• Golden section search method

• Sequential quadratic programming

• genetic algorithm

Illustrate intelligent horizontal machining Center with neat diagram

• The design model of the component to be machined is provided to the computer. 

• Using suitable software, the tool path is generated and the spindle speed and feed rate are decided.

• This information is fed to the machine controller

• The adaptive controller adjusts the feed rate, spindle speed and tool path, according to changes in the cutting conditions.

Illustrate Micro drones

• Frame

• Arms.

• Landing body.

• Camera.

• Battery.

• Motor.

• Gimbal.

Compare basics , strength, technology uses in Alexa and Siri with examples

Alexa

1. Basics:

• Developed by Amazon.

• Primarily used in Amazon Echo and other Amazon smart devices.

2. Strengths:

• Superior smart home control capabilities.

• Robust voice recognition technology.

3. Technology Uses:

• Built on cloud-based AI services.

• Uses AWS for data storage and processing.

• Supports home automation, weather updates, music playback, and shopping.

4. Examples:

• Can control smart home devices

• Allows ordering products from Amazon 

• Provides real-time updates on news, sports, and weather.

Siri

1. Basics:

• Developed by Apple Inc.

• Integrated into iOS devices like iPhone, iPad, Mac, and Apple Watch.

2. Strengths:

• Deep integration with the Apple ecosystem.

• High privacy standards with on-device processing.

3. Technology Uses:

• Utilizes machine learning and natural language processing.

• Supports various functionalities including sending messages, setting reminders, and navigation.

• Integrated with HomeKit for smart home control.

4. Examples:

• Can send texts and make calls using voice commands.

• Provides directions and traffic updates through Apple Maps.

• Controls smart home devices compatible with Apple HomeKit.