Assignment Ict Ai Machine Learning (1) - 084742

ASSIGNMENT: ICT
AI : Machine learning
Submitted To Dr. Hisham Khalill
Submitted by: Anas Ali

AI Machine learning as a concept
Machine learning (ML) is a branch of artificial intelligence (AI) and computer science that
focuses on the using data and algorithms to enable AI to imitate the way that humans
learn, gradually improving its accuracy.
In other words, this process helps the AI model self-learn and perform the desired
outcome.
Three major components have been categorized, the most necessary parts of the learning.
That is done by the model with a little guidance done by the programmer.
Deep Learning
Deep learning plays a significant role in the broader field of AI and machine learning,
offering powerful techniques for learning from large amounts of data and making sense of
complex patterns. Here's how deep learning integrates with AI and machine learning:
1. Feature Learning and Representation: Deep learning excels at automatically learning

representations of data directly from raw inputs. Moreover, deep learning models,
particularly deep neural networks, can learn hierarchical representations of data,
automatically extracting features at different levels of abstraction. This ability to learn
useful representations from raw data is especially valuable in tasks such as computer
vision, natural language processing, and speech recognition. It is clear in the diagram of
flow listed below;
2. Neural Network Architectures: Deep learning is based on neural network architectures

that consist of multiple layers of interconnected nodes (neurons); it resembles the human
mind. These architectures, including convolutional neural networks (CNNs) for spatial
data and recurrent neural networks (RNNs) for sequential data, are designed to handle
complex patterns and dependencies within data. By stacking multiple layers, deep neural
networks can learn increasingly abstract and sophisticated features, enabling them to
capture intricate relationships in the data. As pictorially shown below;
3. Model Training and Optimization: Deep learning models are trained using algorithms like
backpropagation and stochastic gradient descent (SGD). During training, the model's
parameters (weights and biases) are adjusted iteratively to minimize a loss function,
effectively optimizing the model for the given task. Training deep learning models often
requires large amounts of labeled data and significant computational resources. However,
once trained, these models can generalize well to new, unseen data, making them
valuable for real-world applications. As represented here;
In summary, deep learning is a key subset of AI and machine learning that leverages deep
neural network architectures to automatically learn representations from data. Its ability to
handle complex patterns and its broad applicability across various domains make it a
fundamental technology driving advancements in artificial intelligence.
Supervised ML
Supervised machine learning is a type of machine learning where the model is trained on a
labeled dataset, meaning the dataset contains input-output pairs (features and
corresponding target labels). The goal of supervised learning is to learn mapping from input
data to output labels based on the provided examples. Here are three key points about
supervised machine learning:
1. Labeled Training Data: In supervised learning, the training dataset consists of input data
along with corresponding target labels. For example, in a classification task, the input data
might be images of handwritten digits (features), and the target labels would be the actual
digit values associated with each image. The availability of labeled data is crucial for
training supervised learning models. As shown below;
2. Learning from Examples: Supervised learning algorithms learn from examples provided
in the training data. During training, the model adjusts its parameters to minimize the
difference between its predicted outputs and the actual target labels in the training
dataset. It can be represented by a circular flow chart, because steps are often repeating
for further advancement;
3. Generalization to New Data: One of the primary goals of supervised learning is to

generalize well to new, unseen data. After training, the model should be able to make
accurate predictions on data it has not encountered before. Overfitting (when the model
memorizes the training data without truly learning the underlying patterns) is a common
challenge in supervised learning, and techniques such as regularization, cross-validation,
and model evaluation metrics help address this issue. It is explainable by following
example, because all happening is human mind;
In summary, supervised machine learning involves training a model on labeled data to
learn patterns and relationships between input features and target labels. The trained
model can then be used to make predictions or infer outputs for new, unseen data
instances based on the learned patterns. The availability of labeled training data and the
ability of the model to generalize to new data are essential aspects of successful
supervised learning systems.
Un-Supervise learning
1. Finding Similar Groups: Unsupervised learning helps us find groups or clusters in data
that are like each other but different from other groups. Imagine sorting a bunch of fruits
without labels into groups based on their shape, color, and size.
2. Detecting Odd Things: Another use is to identify unusual or odd items in a dataset, like
finding a weird-shaped fruit among a bunch of normal-looking ones. This is useful for
spotting anomalies or outliers in data. As it is clear from the diagram below,
3. Discovering Hidden Patterns: Unsupervised learning can reveal hidden patterns or
relationships in data that aren't obvious at first glance. It's like uncovering connections
between items people frequently buy together at a grocery store without anyone telling you
what to look for. As it is visible from the diagram these detections can make the model
understand better;
In simple terms, unsupervised learning helps us explore and understand data by organizing
it into meaningful groups, spotting unusual things, and uncovering hidden patterns without
needing specific labels or instructions upfront.

Assignment Ict Ai Machine Learning (1) - 084742

Uploaded by

Copyright:

Available Formats

Assignment Ict Ai Machine Learning (1) - 084742

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Assignment Ict Ai Machine Learning (1) - 084742

Uploaded by

Copyright:

Available Formats

ASSIGNMENT: ICT

Submitted To Dr. Hisham Khalill

Submitted by: Anas Ali

1. Feature Learning and Representation: Deep learning excels at automatically learning

2. Neural Network Architectures: Deep learning is based on neural network architectures

3. Generalization to New Data: One of the primary goals of supervised learning is to

You might also like