Notes, summaries, assignments, exams, and problems for Other courses

Combine Independent Unbiased Estimators

Let d₁ and d₂ be independent unbiased estimators of θ with variances σ₁² and σ₂², respectively:

• E[d_i] = θ for i = 1,2.
• Var(d_i) = σ_i².

Any estimator of the form d = λ d₁ + (1 - λ) d₂ is also unbiased for any constant λ.

The variance (mean square error for an unbiased estimator) is
Var(d) = λ²σ₁² + (1 - λ)²σ₂².

To minimize Var(d) with respect to λ, differentiate and set to zero:

d/dλ Var(d) = 2λσ₁² - 2(1 - λ)σ₂² = 0.

Solving gives the optimal weight

λ_* = σ₂² / (σ₁² + σ₂²).

Question 1: Posterior PMF for a Third Dice Roll

Assume there are five dice with sides {4, 6, 8, 12, 20}. One of these five dice is selected uniformly at random (probability 1/5) and rolled twice. The two observed results are... Continue reading "Optimal Estimators, Dice Posterior & Statistical Problems" »

Assembly Language Code Analysis and Solutions

Section 1: Instruction Correctness Check

.data

calculate WORD 100
wVal DWORD 2

Instructions:

1. mov bl, calculate
2. mov ax, wVal

Question 1: Are the above two instructions correct? If not, justify your claim. [2 marks]

Answer:

Both instructions are incorrect.

• For the mov operation, the operands must generally be of the same size.
• In instruction 1, bl is 8 bits (1 byte), but calculate is defined as a WORD (16 bits or 2 bytes). The operand sizes do not match.
• In instruction 2, ax is 16 bits (2 bytes), but wVal is defined as a DWORD (32 bits or 4 bytes). The operand sizes do not match.

Section 2: Loop Pseudo-code

Question 2: Write the pseudo-code for the loop that calculates the sum of the integers 3 + 2 + 1. [2 marks]

Steps for Training a Machine Learning Project in the Cloud

Definition: Cloud ML Project Training

Training an ML Project in the Cloud means utilizing cloud-based resources and services to build, train, and optimize a Machine Learning model.

The Seven Key Steps in Cloud ML Training

1. Data Collection: Gather and upload the dataset to cloud storage.
2. Data Preprocessing: Clean and prepare data using cloud notebooks or specialized processing services.
3. Model Selection: Choose the appropriate algorithm or utilize a pre-built model architecture.
4. Training: Use scalable cloud compute resources (GPUs/TPUs) for intensive model training.
5. Evaluation: Test model accuracy and performance using validation data.
6. Hyperparameter Tuning: Optimize model parameters for better

Basic Protocol Filters

Use these filters to quickly isolate traffic based on common protocols:

• arp (Address Resolution Protocol)
• dns (Domain Name System)
• http (Hypertext Transfer Protocol)
• https (HTTP Secure)
• icmp (Internet Control Message Protocol)
• ip (Internet Protocol)
• ipv6 (Internet Protocol Version 6)
• ntp (Network Time Protocol)
• smtp (Simple Mail Transfer Protocol)
• ftp (File Transfer Protocol)
• ssh (Secure Shell)
• tls (Transport Layer Security)
• udp (User Datagram Protocol)
• tcp (Transmission Control Protocol)
• dhcp (Dynamic Host Configuration Protocol)
• bootp (Bootstrap Protocol)
• radius (Remote Authentication Dial-In User Service)
• snmp (Simple Network Management Protocol)
• kerberos
• smb (Server Message Block)
• nbns (NetBIOS Name Service)
• nbss (NetBIOS Session Service)

Crimes and Criminal Acts Vocabulary

• blackmail – coercion by threat of revealing embarrassing information
• bribery – offering money or gifts to influence someone
• burglary – illegal entry into a building with intent to commit a crime
• drug dealing – selling or distributing illegal drugs
• fraud – deception for personal or financial gain
• hacking – gaining unauthorized access to computer systems
• hijacking – illegally seizing control of a vehicle, especially an aircraft
• kidnapping – abducting and holding someone captive
• mugging – a street robbery, often involving violence
• murder – the unlawful premeditated killing of one human being by another
• rape – non-consensual sexual penetration
• robbery – taking property from a person by force or threat
• smuggling

Aircraft Identification Features

Learn to distinguish different aircraft models by their key visual characteristics:

• A330 vs B777: The B777 doesn’t have winglets, has three wheels per main landing gear strut, and the end of the fuselage is distinct.
• A320 vs B737: Standard Airbus/Boeing differences; B737s have a distinct engine shape (flattened bottom).
• B737 Series: Differences between -200, -300, -400, -500, -600, -700, -800, -900ER are primarily by size.
• B747: All have 4 engines. -200 and -300 do not have winglets, but the -300 has a larger upper deck hump. The -400 has winglets. The SP variant has no winglets and is shorter than others.
• B757: The -300 is significantly larger than the -200.
• B767: The -200 has no winglets. The -400 and -300 have

Evaluation Metrics for ML Models

• Accuracy: The ratio of correctly predicted instances.

• Precision: Correct positive predictions divided by total predicted positives.

• Recall: Correct positive predictions divided by actual positives.

• F1 Score: The harmonic mean of precision and recall.

  

K-Nearest Neighbors (KNN) Algorithm

• A classification algorithm that works by finding the 'k' closest training examples to a data point.

• Strengths: Simple to understand, effective for smaller datasets.

• Weaknesses: Sensitive to irrelevant features and the scale of the data.

• Applications: Image recognition, recommendation systems.

Ensemble Learning Techniques

• Combines multiple models to improve predictive performance.

• Methods:

  • Bagging (e.g., Random Forests)
  • Boosting (e.g., AdaBoost)

Nmap Options

-PE: Quickly check if host is up.

-sn: Disable port scanning (host discovery).

-n: Disables DNS resolution (checks IP online without looking up hostnames).

-O: OS detection.

-A: OS detection, Version detection, Script scanning, traceroute.

-sV: Service detection (banner info, version).

-vV: Provides verbose output.

-sC: Scan with default scripts for additional info gathering.

--min-rate=5000: Ensures scan sends at least 5k packets per second.

nmap --script smb-enum-shares.nse -p 445 (ip): List shares and their properties.

To see scripts starting with X: ls /path/X

To execute script with script tracing: sudo nmap -script=smb-os-discovery -script-trace target_ip

To enumerate the SMB share files: sudo nmap -script=smb-enum-shares target_ip

Vulnerability... Continue reading "Nmap, Netcat, and Metasploit Commands Cheat Sheet" »

First Stage: Gum Pad (Birth to 2 Years)

This stage lasts from birth until the completion of the deciduous maxillary gum pad.

• Maxillary Gum Pad: Horseshoe shape.
• Mandibular Gum Pad: U shape.
• Transverse Division: Elevated ridges are divided into segments for future deciduous teeth.
• Lateral Sulcus: Located distal to the canine area.

Gum Pad Occlusion

Gum Pad at Rest: The pads are not in contact, and the tongue is projecting.

Occlusal relationships are described in three dimensions:

1. Anteroposteriorly (Overjet): Anterior overjet; the mandibular lateral sulcus is posterior to the maxillary.
2. Vertically: Anterior open bite; posterior segments (Segment D) touch.
3. Transversely: The maxillary gum pad is wider than the mandibular (resulting in overjet).

Second Stage: