Rachmaninoff’s family had a musical and military background. At the age of 4, he began piano and music lessons with his mother, then with a professional piano teacher, Anna Ornatskaya. His father, who originally wanted him to pursue a military career, fell into debt and they moved to St Petersburg, where the 10-year-old entered the Saint Petersburg Conservatory. He then transferred to the Moscow Conservatory in 1885 due to his parents separation, and studied under Anton Arensky, Alexander Siloti, and the strict Nikolai Zverev.

In 1892, Rachmaninoff’s final year at the conservatory, he wrote Aleko for his exams, a one-act opera based on the narrative poem The Gypsies. He believed the piece to be a failure, but it was highly successful and earned him a Great Gold Medal and the highest mark. In his debut as a pianist, he premiered his Prelude in C-sharp Minor, one of his most popular pieces. However, in 1897, the premiere of his First Symphony, conducted by Alexander Glazunov was a failure and highly critized. The lackluster performance of the orchestra is believed to be the effect of Glazunov’s incompetence. He fell into a depression following this event and did not compose for 3 years.

Rachmaninoff gradually recovered and composed his Second Piano Concerto in C minor, a piece that would become one of his most celebrated works. He then toured the United States and Europe after composing his third piano concerto and premiering it in New York. He emigrated to the US with his family due to political reasons, focusing on performance. He composed the renowned piece Rhapsody on a Theme of Paganini in 1934, and his last major work — the Symphonic Dances in 1940.

Rachmaninoff was one of the greatest pianists of the time, with strenghts in precision, clear textures and rhythm. He had extremely large hands, making it easy to play even the most complex chords. He recorded some of his works, which can be still be found today. He was both a pianist and a conductor, but decided to focus on piano after he left russia. His compositions was originally influenced bu Tchaikovsky. After his First Symphony, he had the style of highly expressive melodies and chromatic counterpoint. The melodies in his later works are often described melancholy and nostalgic.

Sources:

https://www.worldhistory.org/Sergei_Rachmaninoff/

https://books.google.com.hk/books?hl=en&lr=&id=oiUxDwAAQBAJ&oi=fnd&pg=PP9&dq=rachmaninoff&ots=O30Z9Tv_81&sig=I8K41giFpKEqAMWtD2_pXnMwSs8&redir_esc=y#v=onepage&q=rachmaninoff&f=false

https://www.cambridge.org/core/journals/tempo/article/abs/sergei-rachmaninoff-1873-1943/25ECEE0C99D6F3FDED412BB29B70C939

https://www.classicfm.com/composers/rachmaninov/

Within the ever-changing technology landscape, machine learning stands as a core element with versatile applications spanning across numerous sectors. The task of choosing the right programming language for machine learning projects represents a pivotal decision, impacting efficiency, performance, and scalability significantly. This article explores the pros and cons of different machine learning languages so you can find what’s best for your needs.

1. Python

Python is widely recognized as a favored language for machine learning due to its extensive libraries and user-friendliness.

Advantages:

a. Diverse Ecosystem: Python offers a wealth of libraries, including NumPy, TensorFlow, and PyTorch, which provide essential tools for data manipulation, model development, and training.

b. Strong Community Backing: Python boasts an active community that continually develops and shares machine learning resources and best practices.

c. Versatility: Python is not confined to machine learning; it is also the preferred choice for data analysis, web development, and scientific research.

Disadvantages:

a. Performance: Python’s interpreted nature can result in slower execution when compared to compiled languages like C++ or Java, particularly for computationally intensive tasks.

b. Global Interpreter Lock (GIL): The Global Interpreter Lock (GIL) may restrict Python’s capacity to utilize multi-core processors fully.

c. Memory Usage: Python may consume more memory compared to languages such as C, making it less suitable for resource-constrained environments.

2. R

R is a language designed explicitly for statistics and data analysis, making it an excellent choice for data scientists.

Advantages:

a. Statistical Prowess: R comes with an extensive array of statistical packages, rendering it ideal for in-depth data analysis.

b. Data Visualization: R’s ggplot2 library facilitates beautiful and customizable data visualization.

c. Extensive Documentation: R’s documentation and community resources are tailored to statisticians and data analysts.

Disadvantages:

a. Limited General Purpose Utility: R is primarily geared toward statistical analysis and may not be the best fit for constructing production-ready machine learning systems.

b. Learning Curve: While R is user-friendly for statistical tasks, it might have a steeper learning curve for individuals without previous programming experience.

3. Java

Java is a robust and versatile language frequently chosen for machine learning applications, particularly when performance is paramount.

Advantages:

a. Performance: Java’s compiled nature results in faster execution and reduced memory usage in comparison to interpreted languages like Python.

b. Scalability: Java’s platform independence and robust support for multi-threading make it well-suited for developing scalable, high-performance systems.

c. Enterprise Suitability: Many large-scale enterprises favor Java for its reliability and maintainability.

Disadvantages:

a. Verbosity: Java’s verbosity can lead to lengthier development times and a greater number of lines of code in contrast to Python or R.

b. Learning Curve: Java’s learning curve may be steeper for beginners, especially those with limited prior programming experience.

c. Limited Data Analysis Libraries: While Java offers libraries like Weka and Deeplearning4j, its ecosystem for data analysis is not as comprehensive as Python’s.

4. Julia

Julia is an emerging language specifically designed for high-performance numerical and scientific computing.

Advantages:

a. Performance: Julia delivers performance akin to low-level languages like C and Fortran, while retaining a high-level, user-friendly syntax.

b. User-Friendly: Julia is designed with data scientists and researchers in mind, offering a straightforward and productive environment for machine learning.

Disadvantages:

a. Smaller Ecosystem: Julia’s ecosystem is still in the process of expansion and may not be as extensive as that of Python or R.

b. Limited Legacy Code Compatibility: Transitioning existing projects to Julia may require additional effort.

Each language has it’s own set of strengths and weaknesses so titling one as the “best” isn’t practical for your unique needs. Depending on your own personal preferences along with the critria/purpose of your project, one may suit you better than another. Happy coding!

Sources: https://www.springboard.com/blog/data-science/best-language-for-machine-learning/

The String Family

Situated at the front section of a symphony orchestra, the string family — violins, violas, cello and double bass are played with a bow or plucking the strings. Some common playing techniques include pizzicato (pizz.), plucking the string; arco, playing with the bow after a pizz passage; Col legno, playing with the wooden part of the bow; and sautillé, bouncing the bow off the string to create short and sharp notes. Violins may also have directions to be muted, con sordino (con sord.) meaning with mute and senza sordino (senza sord.) meaning without mute. There may also be instructions for string instruments area of playing, from sul ponticello, playing near the bridge to sul tasto, playing her the fingerboard.

The harp, also classified as a string instrument, usually sits at the left side of the orchestra near the percussion area. Some playing techniques for the harp include bisbigliando, playing repeated notes(tremolo) lightly with both hands, and the direction of pres de la table, directing the player to pluck the string near the soundboard.

The Woodwind Family

The woodwind family has both transposing and non-transposing instruments, where the flute, oboe and bassoon are non-transposing and the piccolo, cor anglais (english horn), clarinet, saxophone, bass clarinet and double bassoon are transposing. Clarinets are often in the key of B flat, A, or E flat. The baritone and alto saxophone are E Flat instruments while the soprano and tenor saxophone are B Flat instruments. A technique in woodwinds is flutter tonguing (flatterzunge), where musicians interrupt the flow of air by rolling ‘r’ when playing. Single-tongue, double-tongue and triple-tongue are also skills used by woodwind players. Apart from the piccolo and the flute, most other woodwinds used reeds to create sound. The oboe, cor anglais, and bassoon are double reeded instruments, while the clarinet and saxophone are single reeded.

The Brass Family

The brass family consists of the trumpet, trombone, bass trombone, tuba and horn, situated at the back of symphony orchestras. The trumpet and horn are transposing instruments while the trombone and tuba are not. Brass instruments may be directed to mute their instruments to produce a different sound, where con sordini [italian]/mit dampfer [german]/ avec sourd [french] meaning with mute and senza sordini/ohne dampfer/otez les sourds meaning without mute. A unique technique for horn players are stopped notes, gestopft [german]/ sons bouches [french], where players push their hand inside the bell of the horn.

The Percussion Family

The percussion family is categorized into those with definite pitch (able to control the pitch) and indefinite pitch (unable to control the pitch). Definite pitch percussion instruments include the timpani, celesta, xylophone, glockenspiel, vibraphone and tubular bells. Indefinite pitch instruments include the bass drum, snare drum, cymbals, gong, triangle and tambourine.

Sources

https://www.dolmetsch.com/musictheorydefs.htm

https://wmich.edu/mus-gened/mus150/Glossary.pdf

https://www.classicfm.com/discover-music/musical-italian-terms/

https://web.archive.org/web/20141022022300/http://www.music.vt.edu/musicdictionary/

Introduction

In recent years, artificial intelligence has made remarkable strides, and one fascinating example of its progress is ChatGPT. Developed by OpenAI, ChatGPT is a cutting-edge language model that has revolutionized the field of conversational AI. In this article, we will explore the history of ChatGPT, its creators, and the capabilities that make it so remarkable.

The Birth of ChatGPT

ChatGPT is based on the GPT-3.5 architecture, which stands for “Generative Pre-trained Transformer 3.5.” The GPT series is a line of language models developed by OpenAI, with each version building upon its predecessor to achieve greater performance and capabilities. The development of ChatGPT has been a continuous process, drawing insights from GPT-1, GPT-2, and other iterations. The iterative nature of the development process allowed OpenAI researchers to identify limitations and shortcomings in previous models, leading to significant improvements with each release.

GPT-1, the first version of the series, introduced the idea of using the transformer architecture for natural language processing tasks. While it showed promise, it had limitations in terms of contextual understanding and coherence. GPT-2 addressed some of these issues and demonstrated the potential of large-scale language models. However, due to concerns about its potential misuse for generating harmful content, OpenAI initially withheld the full release of GPT-2 and only provided access to a scaled-down version.

The release of GPT-3, the third iteration, marked a significant milestone for the GPT series. It featured 175 billion parameters, making it one of the largest language models at the time. GPT-3 showcased extraordinary capabilities in various language tasks, including translation, question-answering, and text completion. Building upon this success, ChatGPT emerged as an extension of GPT-3, specifically fine-tuned to excel in conversational scenarios.

The Creators

OpenAI, a research organization dedicated to creating safe and beneficial AI, is behind the development of ChatGPT. It was founded in December 2015 by Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, Wojciech Zaremba, and John Schulman, among others. Their vision was to advance artificial intelligence in a way that prioritizes the well-being of humanity.

OpenAI’s dedication to ethical AI is evident in their principles, which include a commitment to ensuring that AGI benefits all of humanity. To this end, OpenAI follows a cooperative orientation, actively collaborating with other research and policy institutions to address global challenges posed by AI. The team at OpenAI, consisting of researchers, engineers, and policy experts, brings together diverse expertise to push the boundaries of AI research while responsibly managing its impact.

What is ChatGPT?

At its core, ChatGPT is an autoregressive language model. It is “autoregressive” because it generates text one word at a time, leveraging the context of preceding words to predict the next one. As a “language model,” it understands and predicts patterns in human language. ChatGPT is trained on a vast amount of text data, which enables it to learn grammar, context, and semantic relationships between words.

The training process involves pre-training and fine-tuning. During pre-training, the model is exposed to a wide range of publicly available text from the internet, allowing it to learn grammar, syntax, and factual knowledge. This phase results in a “general” language model that can generate coherent and contextually relevant text.

Following pre-training, the model goes through fine-tuning on specific tasks to make it more useful and controlled. Fine-tuning narrows down the capabilities of the model and tailors it for particular applications, such as chat-based interactions in the case of ChatGPT.

Applications of ChatGPT

The versatility of ChatGPT allows it to be applied in various real-world scenarios, making it a valuable tool for businesses and individuals alike.

Conversational Agents: ChatGPT can power chatbots and virtual assistants, providing natural and engaging interactions with users. It excels at understanding user queries and generating responses that are contextually relevant and coherent, thereby creating an interactive and personalized experience.

Content Generation: Writing high-quality content can be time-consuming and challenging. ChatGPT can assist in writing articles, blog posts, and other forms of content, reducing the burden on human writers. Content creators can use ChatGPT to brainstorm ideas, outline articles, and even receive draft content that they can further refine.

Code Writing: Coding tasks can be made more efficient with the help of ChatGPT. It can generate code snippets based on given requirements, enabling developers to speed up their programming tasks. However, it’s essential to review and validate the generated code to ensure its correctness and security.

Language Translation: Translation between languages is a complex task that requires an understanding of context and nuance. ChatGPT can aid in translating text between different languages, although it might not always match the precision and fluency of professional human translators.

Customer Support: ChatGPT can be utilized in customer support settings to address queries and offer assistance. By integrating ChatGPT into customer service platforms, businesses can provide instant responses to common questions, reducing response time and enhancing customer satisfaction.

Ethical Concerns

Despite its incredible capabilities, ChatGPT has raised some ethical concerns. Being a language model, it can potentially generate misleading or harmful content. It is essential to consider that ChatGPT generates responses based on patterns learned from the data it was trained on, which may include biased or inaccurate information. There is also the risk of malicious use, such as generating misinformation, spam, or abusive content.

Efforts are made by OpenAI to implement safety measures to avoid misuse of the technology. During the development of ChatGPT, reinforcement learning from human feedback (RLHF) has been used to fine-tune the model based on human evaluations and reduce harmful outputs. OpenAI continues to refine and improve these safety mechanisms to make AI systems like ChatGPT more reliable and responsible.

Conclusion

ChatGPT is a remarkable advancement in conversational AI, brought to life by the innovative minds at OpenAI. Its ability to understand and generate human-like text has vast implications across various industries and applications. From assisting content creators to enhancing customer support, ChatGPT demonstrates the transformative potential of language models in our daily lives.

However, as with any powerful technology, ethical considerations are paramount. Responsible development, transparency, and ongoing efforts to mitigate risks are crucial to ensuring that AI like ChatGPT remains a positive force for the benefit of all of humanity. By combining technical excellence with ethical guidelines, we can harness the potential of ChatGPT and similar AI systems to shape a better, more connected future.

Sources:

OpenAI (Official Website) — https://openai.com/

OpenAI Blog — https://openai.com/blog/

GPT-3.5 Paper — “Language Models are Few-Shot Learners” — https://arxiv.org/abs/2005.14165

History of OpenAI — https://en.wikipedia.org/wiki/OpenAI

GPT-3 Overview — https://www.analyticsvidhya.com/blog/2020/12/a-brief-guide-to-gpt-3-openais-powerful-language-model/

In recent years, the rapid advancement of artificial intelligence (AI) and robotics has ushered in a new era of technological innovation. AI, with its ability to simulate human intelligence, combined with the physical capabilities of robots, has brought about remarkable advancements
across various domains. There are many transformative roles of AI in robotics, showcasing its applications in everyday life, space exploration, healthcare, manufacturing, and agriculture. With there being so many amazing uses for AI, it is hard to appreciate how much work and skill is put
into them, even when you don’t even notice.

Robot Vacuums:
Transforming Household Chores
Robot vacuums have become a familiar sight in many homes, revolutionizing the way we clean. These intelligent devices utilize AI algorithms to navigate through rooms, detect obstacles, and efficiently clean floors.

Mars Rovers: Pioneering Exploration Beyond Earth
AI has played a pivotal role in space exploration, enabling robots like the Mars rovers to operate autonomously and collect valuable data. These rovers, equipped with sophisticated AI systems, can make intelligent decisions, analyze terrain, and adapt to unforeseen challenges.

Healthcare Assistants: Enhancing Patient Care
AI-powered robots are transforming the healthcare industry by assisting medical professionals and enhancing patient care. Robots equipped with AI algorithms can perform delicate surgeries with precision, aid in rehabilitation exercises, and provide companionship to patients, especially
the elderly.

Manufacturing Automation: Boosting Efficiency and Safety
In manufacturing, robots empowered by AI algorithms have greatly enhanced efficiency, accuracy, and safety. Collaborative robots, or cobots, work alongside human workers, performing repetitive tasks and handling heavy machinery. AI helps these robots adapt to dynamic environments, optimize workflows, and improve overall productivity.

Agricultural Robotics: Revolutionizing Farming Practices
AI and robotics are revolutionizing agriculture by enabling autonomous farming practices. Smart robots equipped with AI algorithms can monitor crops, optimize irrigation, identify pests and diseases, and perform precision farming. These advancements promise increased crop yields,
reduced environmental impact, and sustainable farming practices.

The integration of AI and robotics is transforming our world, from our homes to outer space, healthcare facilities to manufacturing plants, and farms to everyday life. Through the examples of robot vacuums, Mars rovers, healthcare assistants, manufacturing automation, and agricultural
robotics, we witness the power of AI in enhancing efficiency, accuracy, safety, and overall human experience. As AI and robotics continue to advance, their potential to shape our future remains profound, promising a world where intelligent machines work in harmony with human
capabilities, amplifying our potential to achieve remarkable feats.

Sources:
● “The Impact of Artificial Intelligence in Agriculture” — AgFunder News,
https://agfundernews.com/the-impact-of-artificial-intelligence-in-agriculture.html
● “How Do Robot Vacuum Cleaners Work?” — iRobot,
https://www.irobot.com/learn/robot-vacuums/how-do-robot-vacuums-work
● “Artificial Intelligence in Manufacturing: Present and Future” — Forbes,
https://www.forbes.com/sites/bernardmarr/2018/10/01/artificial-intelligence-in-manufact
uring-present-and-future/
● “The Role of AI in Healthcare Robotics” — World Economic Forum,
https://www.weforum.org/agenda/2018/04/the-role-of-ai-in-healthcare-robotics
● “Mars Rover Curiosity: An Inside Look at AI on Another Planet” — NASA,
https://www.nasa.gov/feature/jpl/mars-rover-curiosity-an-inside-look-at-ai-on-another-pla
net

Terms to learn/look out for include:

Tempo: the rate at which something is performed

Crescendo: a gradual increase in loudness

Cadence: a specific instrument bass that does not have valves

Capella: chorus without music

Pitch: how high and low the music sounds

Chord: several notes played together at the same time

Dynamics: intensity of volume of music

Ballad: a song that describes a story or folktale

Natural Language Processing (NLP) falls under the umbrella of computer science, particularly artificial intelligence (AI), and is concerned with endowing computers with the ability to comprehend text and spoken language much like humans do. NLP employs a combination of computational linguistics, rule-based modeling of human language, and statistical, machine learning, and deep learning models. Using these technologies, computers can process text and voice data and comprehend the meaning, including the speaker or writer’s intent and sentiment. NLP powers computer programs that can translate text from one language to another, respond to spoken commands, and rapidly summarize large volumes of text, even in real time. NLP is present in various consumer conveniences, such as voice-operated GPS systems, digital assistants, speech-to-text dictation software, and customer service chatbots. However, NLP also plays a growing role in enterprise solutions that streamline business operations, increase employee productivity, and simplify mission-critical business processes.

NLP Tasks

Various NLP tasks involve breaking down a human text and voice data into smaller components to help computers comprehend the input. These tasks include:

Speech recognition, or speech-to-text, involves accurately converting spoken language into text. Speech recognition is necessary for any application that processes voice commands or answers spoken queries. The complexity of speech recognition arises from the way people speak — speaking quickly, blending words, using varying intonation and emphasis in different accents, and sometimes using incorrect grammar.

Part of speech tagging, or grammatical tagging, involves identifying the part of speech of a word or phrase based on the context in which it is used. For example, part of speech tagging distinguishes “make” as a verb in “I can make a paper plane” and as a noun in “What make of car do you own?”

Word sense disambiguation involves identifying the correct meaning of a word with multiple meanings by analyzing the context in which it is used. For instance, word sense disambiguation helps distinguish the sense of the verb “make” in “make the grade” (to succeed) versus “make a bet” (to place a bet).

Named entity recognition (NER) involves identifying words or phrases representing essential entities. NER identifies “Kentucky” as a location or “Fred” as a person’s name.

Co-reference resolution involves identifying when two words or phrases refer to the same entity, such as determining the referent of a pronoun (e.g., “she” refers to “Mary”) or identifying a metaphor or idiom in the text (e.g., a “bear” that represents a significant, hairy person).

Sentiment analysis involves extracting subjective qualities from the text, such as emotions, attitudes, sarcasm, confusion, or suspicion.

Natural language generation produces structured information in human language, sometimes seen as the opposite of speech recognition or speech-to-text.

NLP Tools and Approaches

The Natural Language Toolkit (NLTK) is an open-source collection of libraries, programs, and educational resources for building NLP programs. Python programming provides various tools and libraries for tackling specific NLP tasks, many of which are included in the NLTK. These libraries cover various NLP tasks such as sentence parsing, word segmentation, stemming and lemmatization, and tokenization. Additionally, NLTK provides libraries for implementing advanced capabilities such as semantic reasoning.

Initially, NLP applications were hand-coded, rules-based systems that were limited in scalability to accommodate prominent exceptions or increase text and voice data. However, statistical NLP came into existence, which combined computer algorithms with machine learning and deep learning models to automatically extract, classify, and label text and voice data elements. With learning techniques based on convolutional neural networks (CNNs) and recurrent neural networks (RNNs), deep learning models enable NLP systems to ‘learn’ as they work and extract increasingly accurate meaning from massive volumes of raw, unstructured data and unlabeled text and voice data sets.

NLP Use Cases

Many modern real-world applications rely on natural language processing (NLP) for machine intelligence. Some examples include:

Spam detection: NLP’s text classification capabilities scan emails for language that often indicates spam or phishing. This includes overuse of financial terms, lousy grammar, threatening language, inappropriate urgency, and misspelled company names.

Machine translation: Google Translate is an example of widely available NLP technology at work. Effective translation involves accurately capturing the meaning and tone of the input language and translating it to text with the same meaning and impact in the output language. Machine translation tools are making progress in terms of accuracy.

Virtual agents and chatbots: Speech recognition and natural language generation are used to recognize patterns in voice commands or typed text entries and respond appropriately. The best of these also learn to recognize contextual clues over time.

Social media sentiment analysis: NLP analyzes language used in social media to extract attitudes and emotions in response to products, promotions, and events.

Text summarization: NLP techniques digest large volumes of digital text and create summaries or synopses with helpful context and conclusions.

Conclusion

In conclusion, natural language processing (NLP) has become an indispensable tool for machine intelligence in many modern real-world applications. From spam detection to machine translation, virtual agents and chatbots, social media sentiment analysis, and text summarization, NLP’s text classification, semantic reasoning, and natural language generation capabilities are helping to extract insights from unstructured text data and enable machines to understand and respond to human language. With the continued progress in machine learning and deep learning techniques, NLP is poised to play an even bigger role in shaping the future of human-machine interaction and unlocking the potential of big data.

Sources

https://www.ibm.com/topics/natural-language-processing

Algorithm

Process that uses steps to solve a problem. Algorithms are designed by humans and carried out by machines.

Machine learning

A type of AI that predicts outcomes using algorithms to analyze patterns in data (Ex. Ability of cars to warn the driver of obstacles).

Artificial intelligence

Branch of computer science that aims to mimic human intelligence in machines (Ex. Siri or Alexa).

Narrow AI

Most basic level of AI that is designed to solve one problem and carry out a specific task (Ex. Search engines and ChatBots).

Artificial general intelligence

Type of AI that can use its intelligence to solve any problems (Ex. Fictional robots from movies).

This type of AI does not exist yet.

Superintelligence

Type of AI that can solve any problem, replicate human emotions and create decisions on its own.

This type of AI is hypothetical.

Natural Language Generation

Using AI to replicate speech that humans can understand (Ex. ChatBots, Siri and Alexa).

Image Recognition

Ability of AI that identifies people, places and objects in images (Ex. Google Image Search).

Facial recognition

Ability of AI that identifies facial measures mathematically using points on a human face to measure the length or width of a facial feature (Ex. Face identification on phones).

Robotics

Machines powered by AI to carry out specific tasks (i.e. Robot vacuums).

Sources:

Artificial intelligence (AI) algorithms: a complete overview | Tableau. What Is Machine Learning and Why Is It Important?

What Is Artificial Intelligence (AI)? How Does AI Work? | Built In What is robotics?

Natural Language Generation (NLG): Everything You Need to Know What is Facial Recognition? — Definition from WhatIs.com

What Is Image Recognition? Definition from SearchEnterpriseAI

1-Numpy-NumPy is a Python library used for working with arrays.

It also has functions for working in the domain of linear algebra, Fourier transform, and matrices.

NumPy was created in 2005 by Travis Oliphant. It is an open-source project and you can use it freely.

It also stands for Numerical Python.

2-Pandas — It is an open-source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. It is extremely helpful in the field of data science.

3-Keras- Keras is an open-source high-level Neural Network library, which is written in Python and is capable enough to run on Theano, TensorFlow, or CNTK. It was developed by one of the Google engineers, Francois Chollet

4-Pytorch- PyTorch is an open-source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook‘s AI Research lab (FAIR). It is free and open-source software released under the Modified BSD license.

5-Librosa: It is a powerful Python library built to work with audio and perform analysis on it. It is the starting point towards working with audio data at scale for a wide range of applications such as detecting voice from a person to finding personal characteristics from audio.

6-TensorFlow: It is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks

7-Scikit learn: Scikit-learn (Sklearn) is the most useful and robust library for machine learning in Python. It provides a selection of efficient tools for machine learning and statistical modeling including classification, regression, clustering, and dimensionality reduction via a consistent interface in Python. This library, which is largely written in Python, is built upon NumPy, SciPy, and Matplotlib.

8-LightGBM: Gradient Boosting is one of the best and most popular machine learning libraries, which helps developers in building new algorithms by using redefined elementary models and namely decision trees. Therefore, there are special libraries that are designed for fast and efficient implementation of this method.

These libraries are LightGBM, XGBoost, and CatBoost.

9-SciPy: SciPy is a machine-learning library for application developers and engineers. SciPy library contains modules for optimization, linear algebra, integration, and statistics. The main features of the SciPy library are developed using NumPy, and its array makes the most use of NumPy.

10-THEANO: Theano is a computational framework machine learning library in Python for computing multidimensional arrays.

RESOURCES USED:

https://www.bing.com/ck/a?!&&p=127d6378fefc6637JmltdHM9MTY3MTA2MjQwMCZpZ3VpZD0wMGE1Y2RiYy0yMDk0LTYyYzMtM2VmZS1kYzc2MjEzOTYzZTkmaW5zaWQ9NTI2NQ&ptn=3&hsh=3&fclid=00a5cdbc-2094-62c3-3efe-dc76213963e9&psq=scikit+learn+python&u=a1aHR0cHM6Ly9kYXRhZ3kuaW8vcHl0aG9uLXNjaWtpdC1sZWFybi1pbnRyb2R1Y3Rpb24v&ntb=1

Introduction to TensorFlow — GeeksforGeeks

LightGBM (Light Gradient Boosting Machine) — GeeksforGeeks

What Is Scikit Learn In Python — Python Guides

Top 10 Libraries in Python to Implement Machine Learning | HackerNoon

JS stands for JavaScript, which is a scripting language. It can be said that JavaScript is the updated version of the ECMA script. JavaScript is a high-level programming language that uses the concept of OOPS (object oriented programming), but it is based on prototype inheritance.

Vanilla JavaScript:

There is nothing separate about Vanilla JavaScript. “Vanilla JavaScript” refers to plain JavaScript (without frameworks) running against the web API’s as they are exposed by a browser (i.e. client side) runtime.

JavaScript is majorly used in frontend development, which is basically website creation. It is an open-source, flexible, fast, light-weighted framework.

It’s advantages are that VanillaJS allows for cross-compilation and supports interfaces, modules, and classes. It can be used for both frontend and backend development so that it may run on different devices.

Some of its disadvantages are that:

-It makes use of limited libraries.

-Client-side JavaScript doesn’t support writing or reading files. Files are only kept for security purposes.

-A single error may destroy the entire website.

NodeJS:

NodeJS is a cross-platform and open-source JavaScript runtime environment that allows the JavaScript to be run on the server-side. NodeJS allows JavaScript code to run outside the browser. NodeJS comes with a lot of modules and is mostly used in web development.

Some of its advantages are:

-The Node.js library’s APIs are all asynchronous or non-blocking. It simply means that a Node.js based server never waits to return data from an API. After calling an API, the server passes on to the next one, and a Node.js notification mechanism assists the server in receiving a response from the previous API call.

-JS is a quick programming execution library built on the V8 JavaScript Engine in Google Chrome.

However, everything has its own disadvantages.

-One of the big disadvantages of Node.js is its lack of consistency. The API changes regularly, which increases the developers’ problems because they’ll have to make changes to their current code base to maintain compatibility.

-It doesn’t support multi-threading programming, and it is not with the development of heavy computing applications.

However, JavaScript is a very popular programming language. It is very easy to find a resource on JavaScript and do some specific development.

NodeJS is an extension of JavaScript libraries, but it comes with some undefined utilities like non-blocking operating system activity.

In conclusion, there is no real answer as to choosing between VanillaJS versus NodeJS — it all depends on what your project is all about, and what you need to make it successful.

Sources Used

https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&cad=rja&uact=8&ved=2ahUKEwiF89f8nMH7AhXcSGwGHZncBQIQFnoECAoQAQ&url=https%3A%2F%2Fstackoverflow.com%2Fquestions%2F41786986%2Fvanilla-node-vs-express&usg=AOvVaw1V3fr6OhRdmPbOE6Wf0mfa

https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&cad=rja&uact=8&ved=2ahUKEwiF89f8nMH7AhXcSGwGHZncBQIQFnoECCcQAQ&url=https%3A%2F%2Fwww.javatpoint.com%2Fjavascript-vs-nodejs&usg=AOvVaw3JmgTW7hlaWHBDr8HxPNHg

https://www.educba.com/javascript-vs-node-js/

https://www.geeksforgeeks.org/difference-between-node-js-and-javascript/