Deep Learning is a type of Artificial Intelligence (AI) where computers learn patterns from large amounts of data using neural networks (like the human brain).
Similar to Deep Learning is a type of Artificial Intelligence (AI) where computers learn patterns from large amounts of data using neural networks (like the human brain). (20)
PPTX
No need for manual feature selection; deep learning automatically learns feat...
Deep Learning is a type of Artificial Intelligence (AI) where computers learn patterns from large amounts of data using neural networks (like the human brain).
2. Artificial Intelligence
Artificial intelligence (AI) is essentially about making computers "think" like
humans.
It's about creating machines that can learn, solve problems, and make decisions,
just like we do.
Instead of being explicitly programmed for every action, AI systems can learn
from data and improve their performance over time.
3. Machine Learning
Machine learning (ML) is a branch of artificial intelligence (AI) that focuses on
developing systems that can learn from data without explicit programming.
Essentially, ML algorithms analyze data, identify patterns, and make predictions
or decisions based on that data, improving their accuracy over time as they are
exposed to more information.
4. Deep learning
Deep learning is a subfield of machine learning that uses artificial neural networks
with multiple layers (deep neural networks) to analyze data and learn complex
patterns.
These networks are inspired by the structure and function of the human brain and
can automatically extract features from data, making them particularly useful for
tasks like image recognition, natural language processing, and speech
recognition.
7. Aspect Machine Learning (ML) Deep Learning (DL)
Feature Extraction
Manual (human-engineered
features)
Automatic (learned from raw
data)
Process
Data scientists/engineers select
or engineer features based on
domain knowledge (e.g., using
PCA, TF-IDF, statistical
features).
Neural networks (especially
deep ones like CNNs or RNNs)
automatically learn hierarchical
features from data during
training.
Data Input
Requires structured, pre-
processed features as input (e.g.,
tables, extracted attributes).
Raw data (images, text, audio)
can be fed directly into the
model.
Use Case Suitability
Works well with smaller
datasets and tabular data.
Performs best with large
datasets and unstructured data
(images, audio, text).
9. The Importance Of Feature Engineering
Feature engineering is the process of selecting, transforming, or creating
the most relevant variables, known as "features," from raw data to use in
machine learning models.
Transforms Raw Data into Meaningful Inputs: Converts messy or
unstructured data (e.g., text, images) into a structured format usable by
algorithms.
Reduces Model Complexity: By highlighting the most relevant aspects of
data, feature engineering can lead to simpler, faster models.
11. Why is Deep Learning Important?
Handling unstructured data: Models trained on structured data can easily learn
from unstructured data, which reduces time and resources in standardizing data
sets.
Handling large data: Due to the introduction of graphics processing units
(GPUs), deep learning models can process large amounts of data with lightning
speed.
High Accuracy: Deep learning models provide the most accurate results in
computer visions, natural language processing (NLP), and audio processing.
Pattern Recognition: Most models require machine learning engineer
intervention, but deep learning models can detect all kinds of patterns
automatically.
12. How Deep Learning Works
Deep learning uses feature extraction to recognize similar features of the same
label and then uses decision boundaries to determine which features accurately
represent each label. In the cats and dogs classification, the deep learning models
will extract information such as the eyes, face, and body shape of animals and
divide them into two classes.
The deep learning model consists of deep neural networks. The simple neural
network consists of an input layer, a hidden layer, and an output layer. Deep
learning models consist of multiple hidden layers, with additional layers that the
model's accuracy has improved.
13. What is Deep Learning Used For?
Recently, the world of technology has seen a surge in artificial intelligence
applications, and they all are powered by deep learning models. The applications
range from recommending movies on Netflix to Amazon warehouse management
systems.
In this section, we are going to learn about some of the most famous applications
built using deep learning. This will help you realize the full potential of deep
neural networks.
14. Computer Vision
Computer vision (CV) is used in self-driving cars to detect objects and avoid
collisions. It is also used for face recognition, pose estimation, image
classification, and anomaly detection.
15. Automatic Speech Recognition
Automatic speech recognition (ASR) is used by billions of people worldwide. It is
in our phones and is commonly activated by saying "Hey, Google" or "Hi, Siri."
Such audio applications are also used for text-to-speech, audio classification, and
voice activity detection.
16. Translation
Deep learning translation is not limited to language translation, as we are now
able to translate photos to text by using OCR, or translate text to images by using
NVIDIA GauGAN2 .
17. Biomedical
This field has benefited the most with the introduction of deep learning.
DL is used in biomedicine to detect cancer, build stable medicine, for anomaly
detection in chest X-rays, and to assist medical equipment.
