⬅ Back to Home

Unit 1: Introduction to Machine Learning (ML)

Overview of Unit 1

This unit introduces the fundamental concepts of Machine Learning (ML) and its growing impact on various sectors. ML is becoming increasingly integrated into everyday processes, from internet browsing to making financial decisions. The availability of real-time big data allows ML algorithms to learn and make more accurate autonomous decisions. As we explored the past, present, and future of ML, we also discussed the interplay between ML, Artificial Intelligence (AI), and big data analytics. Understanding the role of ML in industry, its associated challenges, and the skills required to work in this field are key objectives of this unit.

Key Learnings

In Unit 1, I gained a comprehensive understanding of:

  • The historical development and future potential of machine learning.
  • The challenges and opportunities presented by using algorithms in various industries.
  • The connection between big data analytics, machine learning, and AI, and how these technologies influence each other.
  • Important skill sets needed to become proficient in ML, including coding, statistical analysis, and data handling.
  • Identifying the pitfalls of machine learning, such as bias in algorithms, and ways to address these issues for better outcomes.

Through this unit, I developed a deeper appreciation for the role of ML in shaping future industries, with a special emphasis on its role in decision-making, automation, and the challenges of keeping up with evolving technologies.

Discussion: Impact of Industry 4.0 on Healthcare

The discussion on Industry 4.0 highlights the transformative potential of technologies such as AI, IoT, and big data analytics in healthcare. These innovations enhance patient care through personalized medicine, continuous monitoring, telemedicine services, and improved operational efficiency. However, the integration of these technologies also brings challenges, particularly in cybersecurity and system reliability.

A central example discussed is the 2017 WannaCry ransomware attack, which disrupted the UK's NHS, causing significant delays in patient care and financial losses. The attack exposed vulnerabilities in outdated systems and highlighted the need for proper patch management and robust cybersecurity protocols. As Yemi Gabriel emphasized, timely security updates and network segmentation could have mitigated the impact of WannaCry. Additionally, phishing awareness through staff training is essential to counter such attacks.

The discussions underline the need for healthcare organizations to strike a balance between leveraging advanced technologies and maintaining strong security protocols. As Noora Alboinin pointed out, adopting Industry 4.0 requires continuous system updates to sustain patient trust and safety while realizing the full potential of digital healthcare.

In summary, while Industry 4.0 presents exciting opportunities for healthcare, organizations must also develop proactive cybersecurity cultures, invest in training, and establish recovery plans. This will help manage risks and ensure the continuity and safety of healthcare services in an increasingly digital landscape.

Unit 2: Exploratory Data Analysis (EDA)

Overview of Unit 2

In Unit 2, I explored the concept of Exploratory Data Analysis (EDA), which is a crucial step in the machine learning process. EDA allows us to understand data through visualization and statistical analysis before diving into modeling. It helps uncover patterns, anomalies, and relationships in the data.

The seminar and readings introduced key techniques for effective EDA, including histograms, scatter plots, and box plots. These visualization tools are instrumental in identifying trends and potential issues such as outliers or missing values. EDA plays a critical role in ensuring the quality of the data before proceeding with more complex analyses.

Readings from Miroslav's "Introduction to Machine Learning" and articles by Patil and Harmadi emphasized best practices, such as thoroughly investigating variable distributions and ensuring data cleanliness. These steps ensure that the dataset is prepared for future modeling and predictions.

Key Learnings

  • Understanding the importance of EDA in ensuring data quality before modeling.
  • Gained familiarity with visualization techniques such as histograms, scatter plots, and box plots.
  • Recognized the importance of data cleanliness and how it impacts machine learning outcomes.
  • Learned to identify outliers and missing values, and how to handle them effectively in datasets.
  • Developed skills in using EDA to uncover patterns and relationships in data.

Unit 3: Correlation and Regression

Overview of Unit 3

Unit 3 focused on the statistical concepts of correlation and regression. Correlation measures the strength and type of relationship between two variables, with methods such as Pearson and Spearman correlation coefficients. Regression, on the other hand, models this relationship as an equation that can predict outcomes based on independent variables.

During the lectures and reading sessions, I learned how to compute correlation and regression, as well as their real-world applications. Regression analysis is particularly useful for making predictions and understanding the dependencies between variables, which can guide decision-making processes in various fields.

The practical application of correlation and regression in this unit has given me the skills to not only understand theoretical concepts but also apply them to data sets for predictive modeling.

Key Learnings

  • Developed an understanding of Pearson and Spearman correlation coefficients.
  • Learned how to compute and interpret correlation in real-world datasets.
  • Gained insights into regression modeling to predict outcomes based on independent variables.
  • Understood how to apply regression techniques to guide decision-making processes.
  • Enhanced skills in applying statistical techniques to datasets for predictive modeling.

Ethical Considerations and Professional Issues

In this unit, I explored how biased datasets could influence the outcomes of correlation and regression analyses. For example, biased or incomplete datasets can result in incorrect predictions, especially in critical fields like healthcare or financial decision-making, where the stakes are high. Ensuring that data is representative and transparent is crucial to minimizing these risks.

Furthermore, the interpretation of correlation results can lead to misleading conclusions if not approached cautiously. It is important to recognize the ethical responsibility of using these models professionally, ensuring that stakeholders understand the limitations and assumptions behind the models.

From a professional perspective, ensuring transparency and accountability in machine learning practices, especially with sensitive data, is essential to building trust in AI models and their predictions.

Unit 4: Linear Regression with Scikit-Learn

Overview of Unit 4

In Unit 4, I explored the fundamentals of linear regression and learned how to apply this technique using Python’s Scikit-Learn library. Linear regression helps us model the relationship between dependent and independent variables, making it a powerful tool for predicting outcomes.

Key Learnings

In this unit, I covered:

  • How to model simple linear relationships between a single independent variable and a dependent variable.
  • Developing multivariate linear regression models, where multiple independent variables are used to predict a single dependent variable.
  • How to evaluate the accuracy of a linear regression model using metrics like R-squared values and residual analysis.
  • Best practices for optimizing models, including handling large datasets and addressing potential issues like multicollinearity.

By using Scikit-Learn, I was able to efficiently implement linear regression and apply these models to real-world data. The hands-on activities in Jupyter Notebook were invaluable for reinforcing the concepts covered in the readings.

Applications and Challenges

One of the key applications of linear regression is in financial risk modeling, as illustrated in the additional reading by Valaskova et al. (2018). The study provided insights into how regression models are used to predict financial risk in business environments, emphasizing the importance of accurate data and model selection.

The readings also highlighted the challenges faced when working with regression models, particularly in ensuring that the relationship between variables is linear and that the dataset is suitable for regression analysis. This emphasizes the importance of understanding data patterns before applying machine learning models.

Unit 5: Clustering

Overview of Unit 5

This unit introduced the fundamental concept of clustering, where objects are grouped into clusters based on their similarity. Clustering is widely used in fields such as image analysis, pattern recognition, and machine learning for identifying patterns in data.

Key Learnings

In Unit 5, I covered several important topics, including:

  • The basic idea behind clustering and how it fits within exploratory data analysis.
  • Different techniques for measuring the distance or similarity between points, such as Euclidean distance and the Jaccard coefficient.
  • K-means clustering, which minimizes the variance within clusters, and agglomerative clustering, a hierarchical method.
  • How to evaluate clusters using methods like the Silhouette score and Sum of Squared Errors (SSE).

Through hands-on activities, I applied clustering techniques and evaluated the results, gaining practical experience in grouping datasets and understanding the factors that influence the success of these methods.

Applications and Challenges

Clustering can be applied in many fields, from bioinformatics to computer graphics. However, the process is not without challenges. Choosing the right number of clusters, handling large datasets, and evaluating the quality of the clusters are all critical considerations when working with this technique.

In this unit, I also calculated the Jaccard coefficient for various pairs of individuals based on binary data. The Jaccard coefficient measures the similarity between sets, and I applied it to determine the level of similarity between individuals with different test results. This exercise helped me understand how to apply clustering to categorical data in real-world scenarios.

Unit 6: Clustering with Python

Overview of Unit 6

In Unit 6, I applied the K-means clustering algorithm using Python's Scikit-learn library. This practical unit allowed me to use K-means on real datasets, grouping similar data points into clusters and interpreting the results.

Key Learnings

Throughout this unit, I gained experience with:

  • The functionalities of the Scikit-learn library for implementing K-means clustering.
  • How K-means minimizes variance within clusters to form distinct groupings.
  • Using Python libraries efficiently to analyze large datasets.
  • Evaluating clustering results using metrics such as inertia and Silhouette scores to measure cluster cohesion and separation.

This unit enhanced my ability to conduct clustering analysis on complex datasets and provided practical insights into evaluating and optimizing K-means models.

Applications and Challenges

K-means clustering is highly applicable in various fields, from customer segmentation to image compression. However, one of the main challenges in clustering is choosing the right number of clusters (k) and ensuring that the clusters are meaningful in the context of the data. This week, I focused on interpreting the results to answer questions about the dataset and identifying areas where clustering might lead to insights or require adjustment for better accuracy.

Ethical Considerations and Professional Issues

During this unit, ethical challenges related to data usage and clustering became apparent. One of the key issues was ensuring that the clustering process does not introduce biases. For example, using biased datasets can lead to unfair groupings or classifications in fields such as healthcare or finance. Another concern is the handling of large datasets, which may contain sensitive personal information. Ensuring data privacy and protecting individual rights are crucial in professional environments where clustering algorithms are applied.

In professional practice, transparency and fairness in algorithmic decision-making must be prioritized to avoid unjust outcomes or discrimination. This unit reinforced the importance of critically evaluating the datasets used for machine learning models and ensuring adherence to ethical guidelines, particularly when dealing with personal data.

Development Team Project

Team Meeting Notes

Throughout our group project, we held several team meetings to discuss task allocation, progress tracking, and problem-solving strategies. Below is a brief outline of the key points from our team meetings:

  • Initial Meeting: We discussed the project objectives, assigned tasks based on each member's strengths, and set up a shared Google Drive for collaboration.
  • Second Meeting: Focused on data collection and cleaning. We encountered challenges with missing data and discussed potential imputation techniques.
  • Final Meeting: Finalised our report and prepared the visualizations for submission. We agreed to review each section before the deadline to ensure consistency.

Click here to view the full meeting notes and group contract.

Feedback Summary

Our group project report on Airbnb’s listing performance received valuable feedback. The project aimed to investigate whether the length of an Airbnb listing title correlates with its performance. We were commended for framing a relevant business question and providing clear visualizations, but there are several areas for improvement:

  • Rationale for the Business Question: While the question was appropriate, the rationale for selecting the title length as a key variable could have been critically assessed.
  • Expected Business Impact: More detailed discussion on the broader business strategy implications was necessary.
  • Methodology: The basic statistical methods were well-applied, but more advanced techniques like multivariate analysis could have added depth.
  • Visualisations: Effective, but more comprehensive explanations were needed for clarity.

Action Plan

Based on the feedback received, I plan to improve my critical analysis and methodological depth in future projects. Specifically, I aim to:

  • Explore multivariate analysis techniques for more complex datasets.
  • Provide more detailed rationales for variable selection and analysis methods.
  • Ensure that all visualisations include thorough explanations for better interpretability.

Click here to view the full feedback document provided by our tutor.

Unit 7: Introduction to Artificial Neural Networks (ANNs)

Overview of Unit 7

This unit introduced artificial neural networks (ANNs), focusing on key concepts like activation functions and weight adjustments, which are critical for processing inputs and fine-tuning the network.

Key Learnings

In this unit, I learned about:

  • The role of activation functions, such as the Sigmoid function, in determining network outputs.
  • How weight adjustments are used during training to improve model accuracy.
  • Practical implementation of Perceptron models using Python.

Unit 8: Training an Artificial Neural Network

Overview of Unit 8

This unit focused on how artificial neural networks (ANNs) learn from their errors using backpropagation. Backpropagation helps adjust the weights of neuron connections, enabling the network to improve its performance by minimizing errors.

Key Learnings

In this unit, I covered:

  • How backpropagation adjusts weights to improve ANN accuracy.
  • Real-life applications of ANNs in various industries.
  • The importance of error handling and training mechanisms in ANN development.

Discussion 2: Legal and Ethical views on ANN applications

In my initial post, I discussed the integration of AI writers, or "robo-writers," across various industries. I highlighted both the benefits and risks that come with using AI for tasks ranging from administrative documentation to creative writing. According to the *Future of Jobs Report 2023* by the World Economic Forum, 75% of companies plan to adopt AI tools within the next five years, driven by the efficiency and innovation AI brings to different sectors.

The key benefits I focused on include how AI writers can handle repetitive tasks like generating reports and standard communications, which can free up human employees to focus on more strategic, creative, and analytical roles (Roland Berger, 2017). Additionally, AI can support the creative process by helping with brainstorming, structuring content, and even generating narratives (Li & Liu, 2018). AI is also transforming research, automating literature reviews and summarizing findings, making it a valuable tool for research-heavy industries (Turck, 2020).

However, I also raised concerns about the risks of relying on AI writers. One of the major risks is the potential for misinformation. AI systems, though advanced, aren't always accurate and may generate content that seems convincing but is factually incorrect, which is particularly dangerous in fields like healthcare or law (Turck, 2020). Another concern I mentioned is the ethical dilemma surrounding authorship and ownership of AI-generated content. The lack of clear guidelines could lead to disputes and challenges regarding who owns the rights to this content (Kubat, 2021). I also expressed concern that relying too heavily on AI for creative tasks might dilute human originality and authenticity (World Economic Forum, 2023).

In conclusion, while AI writers offer significant benefits in terms of efficiency and support for creativity, it’s important that we carefully manage the associated risks. I believe organizations should establish clear guidelines to ensure ethical use of AI, focusing on transparency, accuracy, and accountability.

References:

  • Kubat, M. (2021). *An Introduction to Machine Learning* (3rd ed.). Springer.
  • Li, D., & Liu, Y. (2018). *Deep Learning in Natural Language Processing*. Springer.
  • Roland Berger. (2017). *Trend Compendium 2030: Dynamic Technology and Innovation*.
  • Turck, M. (2020). *Data and AI Landscape 2020*. FirstMark.
  • World Economic Forum. (2023). *Future of Jobs Report 2023*. Available from: https://www.weforum.org/reports/the-future-of-jobs-report-2023 [Accessed 3 October 2024].

Unit 9: Convolutional Neural Networks (CNNs)

Overview of Unit 9

This unit focused on Convolutional Neural Networks (CNNs), an extension of artificial neural networks designed for computer vision tasks. CNNs are used in various real-life applications like self-driving cars and medical image analysis, where machines learn to recognize and interpret visual information.

Key Learnings

In this unit, I learned about:

  • The algorithms and layers that make up CNNs.
  • Using CNN-specific Python libraries for image recognition tasks.
  • The real-world applications of CNNs in industries such as healthcare and transportation.

Unit 10: Interactive Learning with Convolutional Neural Networks (CNNs)

Overview of Unit 10

This unit focused on gaining a deeper understanding of Convolutional Neural Networks (CNNs) through the CNN Explainer platform. This interactive tool allowed me to explore the internal structure of CNNs, including how different layers process visual data and make predictions.

Key Learnings

In this unit, I learned about:

  • How to interactively explore CNN layers and architectures using the CNN Explainer tool.
  • Understanding CNNs in greater detail by adjusting parameters and visualizing their impact on image recognition tasks.
  • The practical applications of CNNs in tasks such as object recognition and computer vision.

Unit 11: Model Selection and Evaluation

Overview of Unit 11

This unit focused on the importance of selecting the right machine learning model for a given task and evaluating its performance. The goal was to understand how different models behave and to improve them through systematic evaluation and optimization techniques.

Key Learnings

In this unit, I learned about:

  • The workflow of selecting appropriate models for prediction or classification tasks.
  • How to evaluate models using various metrics to assess their strengths and weaknesses.
  • Techniques for optimizing model performance by identifying areas of improvement and refining predictions.

Unit 12: Industry 4.0 and Machine Learning

Overview of Unit 12

This unit explored the concept of Industry 4.0, which refers to the fourth industrial revolution characterized by the integration of intelligent systems and machine learning into industrial processes. We discussed how machine learning is applied to monitor assets, optimize operations, and create digital twins for predictive analysis.

Key Learnings

In this unit, I learned about:

  • The transformative impact of Industry 4.0 on manufacturing and other industries.
  • How machine learning algorithms are deployed to improve efficiency and decision-making.
  • The concept of digital twins and their role in monitoring and optimizing industrial assets.
  • Job opportunities and challenges emerging in the Industry 4.0 era, particularly regarding automation and AI.

Seminars

Access All Seminars

You can access all seminar materials through the following link:

Seminar Materials - Google Drive

Seminar 1: Introductory Session (Unit 1)

This session introduced the Machine Learning module, focusing on the basics of the 4th Industrial Revolution and its relevance to AI and ML. The seminar outlined the core objectives of the module and provided an overview of key concepts, such as Industry 4.0, automation, and machine learning applications in various sectors.

Seminar 2: Exploratory Data Analysis Tutorial (Unit 2)

This session focused on Exploratory Data Analysis (EDA), its importance in data science, and its role in identifying trends, patterns, and anomalies before any predictive modeling. Hands-on activities included using Python libraries like Pandas and Matplotlib to visualize data through histograms and scatter plots.

Seminar 3: Regression and Scikit-Learn (Unit 4)

In this seminar, the focus was on linear regression, using Scikit-Learn to model relationships between dependent and independent variables. Topics covered included training models, residual analysis, and evaluating the performance of regression models.

Seminar 4: K-Means Clustering Tutorial (Unit 6)

The seminar was centered around K-means clustering, a fundamental technique for grouping data points into clusters based on their similarity. Students learned about different metrics used to evaluate clustering performance, including inertia and the Silhouette score.

Seminar 5: Emerging Research in ANN (Unit 8)

This session introduced Artificial Neural Networks (ANNs) and the process of training neural networks. The seminar emphasized practical applications in different industries and research advancements in ANNs, such as their use in image and speech recognition.

Seminar 6: CNN Tutorial (Unit 10)

This session focused on Convolutional Neural Networks (CNNs) and their application in computer vision tasks such as image classification. The tutorial included hands-on activities with the CNN Explainer tool and explored the layers within CNNs like convolutional and pooling layers.

Seminar 7: Future of Machine Learning (Unit 12)

This seminar explored the future of machine learning, especially in the context of Industry 4.0. It covered emerging trends such as the use of deep learning, reinforcement learning, and predictive modeling in industries. Ethical considerations and professional issues related to AI were also discussed, particularly the impact of AI on the workforce and privacy concerns.

Professional Skills Matrix and Action Plan (PDP)

The Professional Development Plan (PDP) is a framework I developed to monitor my skill acquisition and set clear objectives for personal and professional growth throughout this module. Below is a skills matrix outlining my current competencies and the actions I plan to take for further development.

Skills Matrix

Skill Current Proficiency Development Objective Action Plan
Machine Learning Techniques Intermediate Advance to expert-level proficiency Engage in additional hands-on projects using Python libraries (e.g., Scikit-Learn, TensorFlow), study advanced algorithms, and take online courses.
Teamwork & Collaboration Proficient Enhance leadership and task management skills Take a leadership role in team projects, improve communication, and develop better task distribution strategies.
Data Preprocessing & EDA Intermediate Improve data cleaning and visualization skills Focus on using tools like Pandas and Matplotlib for data manipulation, and complete additional exercises on handling missing data, outliers, and data wrangling.
Ethical AI Development Basic Develop a deeper understanding of ethical implications in AI Study case studies on biased AI algorithms, attend AI ethics webinars, and collaborate with peers to evaluate ethical challenges in machine learning projects.

Action Plan

The following actions are designed to help me meet the development objectives outlined in the skills matrix:

  • Hands-on Projects: I plan to undertake at least two advanced machine learning projects focusing on real-world datasets to improve my technical proficiency.
  • Leadership Role: In future group projects, I will take a more active role in task management, ensuring that roles are well-defined and deadlines are met.
  • Data Processing: I will complete several guided exercises on data cleaning, visualization, and feature engineering to enhance my skills in preparing datasets for machine learning models.
  • Ethics in AI: I will participate in discussions and courses focusing on AI ethics, exploring how to build transparent and fair machine learning models.

Reflection

WHAT: Critical incidents and project outcomes

I worked with important machine learning methods during this session and gained hands-on experience in neural networks, clustering, and exploratory data analysis (EDA). Gaining practical expertise with machine learning algorithms on real-world datasets was the main objective of these exercises. Data preparation was one of the crucial situations I ran into early on. I came across a number of problems when working on a dataset for a machine learning project, such as missing values and outliers, which had a big impact on how well the models I used—like K-means clustering and linear regression—performed. The significance of appropriate data preparation and cleaning, which are essential for guaranteeing precise and trustworthy outcomes in any machine learning work, was highlighted by this circumstance.

The group project, which involved cooperation with my classmates to apply machine learning techniques to address a real-world problem, was another important component of the program. Early on in the project, our team had trouble communicating and allocating tasks. Roles and responsibilities were unclear, which resulted in inefficiencies and an unequal distribution of the workload. However, the team adjusted by enhancing communication and clearly defining each member's job after considering our development and getting input from tutors. This change was essential to making sure that everyone participated equally in the process and that we finished the project successfully.

SO WHAT: Interpretation and Analysis

I learnt a lot from the difficulties I had with data preprocessing during the project. When I saw how badly prepared data resulted in unsatisfactory model performance, it became evident to me how important high-quality data is to machine learning. Outliers and missing numbers, in particular, can skew the results of even the most advanced algorithms. I learnt from my experience with EDA how important it is to fully examine and comprehend the dataset before using any machine learning models. I was able to better prepare the data for analysis by visualising it, finding trends, and spotting irregularities.

Furthermore, my practical knowledge of Python tools like Pandas and Matplotlib significantly improved my capacity for data management and cleaning. For example, I applied imputation techniques to address missing data during EDA and eliminated outliers that affected the accuracy of the model. This procedure not only enhanced the K-means clustering algorithm's performance but also gave me more confidence to use these crucial tools in projects in the future.

The group assignment gave me a great chance to hone my cooperation and teamwork abilities. The difficulties of group work, especially in a virtual environment, were first made evident by our team's difficulties with communication and task distribution. Nevertheless, we were able to reorganise our strategy to more effectively oversee the project after getting input and considering our group dynamics. By instituting frequent check-ins, we enhanced communication and made sure that everyone on the team understood their roles. Because of this adjustment, our workload was more evenly distributed, and we were able to finish the project faster.

The module discussions on bias in machine learning algorithms were especially instructive in terms of professional and ethical development. I learnt more about the moral dilemmas raised by biassed datasets and how they might result in unfair outcomes—particularly in delicate fields like healthcare or hiring—through case studies and group discussions. As I grew to understand how crucial it is to make sure that models are not only accurate but also equitable and transparent, the ethical implications of machine learning became a major topic of reflection for me. This knowledge will be crucial for my future work, since I plan to pay closer attention to the moral implications of the models I create.

NOW WHAT: Applying Knowledge and Next Steps

My future career development will be greatly impacted by the information and abilities I acquired from this training. My current position and future professional goals will benefit greatly from my technical machine learning skills, especially in data preprocessing, model evaluation, and using Python libraries. The significance of meticulous data preparation and cleansing is one of the main lessons I learnt from this program, and I will keep using it in my professional job. My comprehension of how EDA and data wrangling can greatly increase the precision and dependability of machine learning models has much improved, and I intend to apply these techniques in all upcoming projects.

I also intend to investigate more sophisticated machine learning methods, such as neural networks and deep learning models, in order to expand on the fundamental information I acquired in this session. Although I only completed the course's introductory activities, I am excited to learn more about neural networks. I really want to investigate how neural networks can be used to solve practical issues like commercial customer behaviour research or predictive maintenance in industrial settings.

I learnt a lot about cooperation and project management from my experience working in a team on the project. I will take more care to create clear lines of communication and make sure that everyone on the team has a clear role in any future projects, whether they are academic or professional. Our project benefited greatly from the use of frequent progress reports and explicit task distribution, and I want to implement these techniques in subsequent group projects. The value of flexibility and adaptability in teamwork has also been emphasised by this experience, since any collaborative project's success depends on the team's capacity to modify plans and strategies when difficulties emerge.

My future approach to model construction will be influenced by the ethical lessons I've learnt about bias in machine learning. My comprehension of the possible repercussions of biassed data and how it can result in discriminating conclusions has increased. I intend to be more proactive in spotting and resolving bias in datasets and algorithms in my future work. This will entail not just technical fixes, including making sure training data is varied and representative, but also taking into account the models' wider social and ethical ramifications.

To sum up, this module has been a life-changing experience that has improved my technical proficiency as well as my growth on the personal and professional fronts. A thorough grasp of machine learning methods and their practical applications was made possible by the integration of academic education with hands-on practice. I am eager to use the knowledge I have acquired in next projects and to keep improving my abilities in this field. The principles I learnt from this subject will have a long-lasting effect on my work, whether it is through tackling ethical issues, investigating sophisticated machine learning models, or refining data pretreatment approaches.

References

  • Kubat, M. (2021). An Introduction to Machine Learning (3rd ed.). Springer.
  • Li, D., & Liu, Y. (2018). Deep Learning in Natural Language Processing. Springer.
  • Novaković, J.Dj., Veljović, A., Ilić, S.S., Papić, Z., & Milica, T. (2017). Evaluation of Classification Models in Machine Learning. Theory and Applications of Mathematics & Computer Science, 7(1), 39-46.
  • Wang, J., Turko, R., Shaikh, O., Park, H., Das, N., Hohman, F., Kahng, M., & Chau, P. (2021). CNN Explainer: Learn Convolutional Neural Network (CNN) in your browser.
  • Turck, M. (2020). Data and AI Landscape 2020. FirstMark.