Week 7 Assignment AVD
Week 7 Assignment AVD
Week 7 Assignment AVD
Sirichandana Nannuri
Business Intelligence
The potency of Artificial Intelligence (AI) is harnessed through a dynamic progression that
amalgamates data, algorithms, and computational prowess. This procedure commences with the
accumulation of extensive and varied datasets from sources like sensors, devices, and databases.
The amassed data undergoes preprocessing, which involves cleansing, transforming, and
organizing to guarantee its quality and pertinence. Crucial attributes are then distilled or chosen
to generate meaningful representations. The crux resides in the selection of suitable algorithms
based on the problem's nature, spanning from machine learning to deep learning
methodologies. The training of models encompasses exposing algorithms to the prepared data,
enabling them to comprehend patterns and associations. This trained model is meticulously
assessed for performance utilizing distinct data. Once a contented model is achieved, it's put
into action in real-world scenarios to furnish forecasts, categorizations, or recommendations.
Continual feedback from real-world outcomes refines the model over time, augmenting its
precision and applicability. Essentially, the might of AI emerges from the fusion of data-driven
learning, intricate algorithms, and iterative enhancement, culminating in systems capable of
recognizing patterns, learning from experience, and facilitating decision-making across diverse
domains.
Other Differences:
Representation of Data:
Machine Learning (ML): ML algorithms rely on handcrafted features extracted from the data.
Feature engineering is a crucial step, where domain knowledge helps in selecting relevant
features for the model.
Deep Learning (DL): DL algorithms automatically learn hierarchical representations of data
through multiple layers of neural networks. This eliminates the need for extensive feature
engineering, as the network learns relevant features by itself.
Model Complexity:
ML: ML models are generally simpler and have fewer parameters compared to DL models. They
may struggle to capture intricate patterns in highly complex datasets.
DL: DL models are complex due to their deep architecture, making them capable of capturing
complex patterns and relationships in large and high-dimensional datasets.
References:
1. https://www.geeksforgeeks.org/difference-between-machine-learning-and-deep-learning/
2. https://www.researchgate.net/publication/
350834453_Machine_learning_and_deep_learning#:~:text=Machine%20learning
%20describes%20the%20capacity,based%20on%20artificial%20neural%20networks.
3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). "Deep Learning." MIT Press.
4. Bishop, C. M. (2006). "Pattern Recognition and Machine Learning." Springer.
5. LeCun, Y., Bengio, Y., & Hinton, G. (2015). "Deep learning." Nature, 521(7553), 436-444