Transcript:
[MUSIC] Hello, everyone and welcome to this interesting video on machine learning tools. So the era of machine learning is here and it’s making a lot of progress in the technological field and according to a gardener report, machine learning and artificial intelligence is going to create 2.3 million jobs by 2020 and Machine Learning Inc. °o° system has developed a lot in the past decade. The AI community is so strong open and helpful that there exists, court library and blog for almost everything. If you want to start a journey in this magical world now is the great time to start, so we are going to discuss some of the machine learning tools and we’ll discuss an exhaustive list of libraries and tools to handle most of the machine learning tasks so before that, let’s understand. What exactly is machine learning? Machine learning is a type of artificial intelligence that allows software applications to learn from the data and become more accurate in predicting outcomes without human intervention machine. Learning is a concept which allows the machine to learn from examples and experience and active without being explicitly programmed to make this happen. We have a lot of machine learning tools available today. So the first tool which? I’m going to talk about is scikit-learn. It’s not exactly a tool. It’s a library. But it’s the initial steps which one should follow so scikit-learn is a free software machine learning library for the Python programming language. It is a simple and efficient tool for data, mining and data analysis It has built or numpy. Syfy and Matplotlib. It provides a range of supervised unsupervised machine learning algorithms in Python like classification regression, clustering, the dimensionality reduction and much more, so this is one of the basic steps or the basic building block of any machine learning project or application out there. So you need to know Scikit-learn. This is one of the most important tool next. I’m going to talk about ASCII Nemetes Constants Information Minor. It is a free and open source data analytics, reporting and integration platform, which is built for powerful analytics on a GUI based workflow. This means you do not have to know how to code to be able to walk using the K-9 and derive the insights What you can do is you can walk all the way from gathering the data and creating models to deployment as well as production, it consolidates all the functions of the entire process into a single workflow You can gather and wrangle the data you can model and visualize you can deploy and manage and you can consume and optimize as well, so it’s an all-in-one package and the most important aspect is you do not need to know how to code, so the next library, which I’m going to talk about is one of the best library out there for machine. Learning that just stands a flow. It is created by Google Brain team and tensorflow. It’s an open source library, file numerical computation and large-scale machine learning when it comes to artificial intelligence framework showdown. You will find tensorflow emerging as a clear winner most of the time. Now what makes it so special? So Tensorflow provides an accessible and readable syntax, which is essential for making these programming resources easier to use and being a low-level library provides more flexibility and with the new version of 2.0 It is just going to be on the top of any machine. Learning or deep learning purposes, it is one of the best machine learning tools available and it also uses chaos and other high-level apis to make things little smoother and the most important thing is it can run on both CPU as well as GPU, and it really helps in graphical purposes. Like if you are dealing with images videos, Tensorflow is the way to go now. Vica, which is the Waikato Environment For Knowledge Analysis, It is an open source Java software that has a collection of machine learning algorithms for data, mining and data exploration tasks. It is one of the most powerful machine learning tools for understanding and visualizing machine learning algorithms on your local machine. It has both a graphical interface and a command-line interface. Now, the only downside to this is that there is not much documentation or online support available, but all in all, it’s a very good software and it’s based on Java. It also provides predictive modeling and visualization and it’s an environment for comparing learning algorithms, and the graphical user interface includes data visualization as well now next we have a library, which is one of the biggest rival of tensorflow, which is Pi Torch or torch so Pi Tache is a python-based library built to provide flexibility as a deep learning deployment platform. The workflow of Pi Taj is as close as you can get to the Python Scientific Computing Library Numpy. It is actively used by Facebook for all of its machine. Learning or deep learning work and the dynamic computation graphs are a major highlight of Python. The support for CUDA ensures that the code can run on the GPU, thereby decreasing the time needed to run the code and increasing the overall performance of the system. Now this framework is embedded with ports to ios and Android backends, a rapid miner, the next tool, which I’m going to talk about is a data science platform for teams that unite’s data preparation, machine learning and predictive model deployment. It has a powerful and robust and graphical user interface that enables user to create, deliver and maintain predictive analytics with rapid miner uncluttered, disorganized and seemingly useless data becomes very valuable as it simplifies data access. And lets you structure them in a way that is easy for you and your team to comprehend now. Few of the features are that it results in visualization A lot through Gy it helps in designing and implementing analytical workflows. One of the downside is that the tool is very costly now. Google is not very far behind apart from tensorflow. We have the Google Cloud Auto ML now. Google Cloud Auto ML makes the power of machine learning available to you. Even if you have limited knowledge of machine learning, the Google’s human labeling service can put a team of people to work annotating or cleaning your labels to make sure your models are being trained on high quality data now. How cool is that? They have various products for different purposes, which makes it a very good machine learning tools. For example we have. Auto ML vision, which is used for images, we have the auto ML video intelligence, which is specifically designed for video. We have the auto ML natural language, which is used to structure and get the meaning of text. We have the auto ML translation, which dynamically detects and translate between different languages. And we have the auto ML tables, which means the models on your structured data now. We have the asure machine learning studio as well now. Microsoft Azure Machine Learning Studio is a collaborative drag-and-drop machine learning tool you can use to build test and deploy predictive analytics solution on your data, you drag-and-drop paid assets and analysis modules into an interactive canvas and connecting them together to form an experiment which you run in the machine learning studio and there is no programming required just visually connecting data sets and modules to construct your predictive analytic model And finally you just have to publish it as a Web service now a cord on it is a dotnet machine learning framework combined with audio and image processing libraries, which is completely rewritten in Sisha now. The tagline being machine learning made in a minute. That’s an amazing tagline guys. And it is a complete framework for building production, great computer vision, computer audition, signal processing and statistics application libraries are made available from the source code and through executable installer and the new gate packet manager. The only drawback is that it supports dot that it only supports the dotnet supported languages. It provides algorithm for numeric linear algebra numerical optimization statistics artificial neural network. It also provides supports for graph plotting and visual libraries as well and it has more than 38 kernel function. It contains more than 35 hypotheses tests, including one way and the two way. Anova test nonparametric tests like called Makarov’s Mironov test and many more. Now this is rather an interesting product by Google, which is the core laboratory. It is a free Jupiter notebook environment that requires no setup and runs entirely on the cloud. It is a Google research project created to help decimate machine learning, education and research. That’s a good step forward by Google, it is by far one of the top machine learning tools, especially for data scientists because you don’t have to manually install any of the package and Lavery’s just import them directly by calling them. You can directly save a project on the Google Drive Github or any location in various formats as well and it also supports libraries of Pi Taj Karas tensorflow as well as open CB. These are pre-installed now. This is a major step forward in the Machine Learning Education Department by Google, so hats off to them. NL DK is another tool which I’m going to talk about, which is the natural language toolkit and it’s an extensive library for natural language tasks. It just a core to package for all your text processing needs from word tokenization to limit ization stemming in dependency parsing chunking chinking, removing the stop words and many more text processing is an extremely important part for any NLP task like language modeling, neural machine translation or named entity recognition, and it also provides a synonym Bank called divergent. Now these are a few of the tools, basically, the libraries and the frameworks which are really really necessary if we are going for machine learning or if you’re going for deep learning as a matter of fact, and these lists of tools are enough for anyone to get started in the machine learning world so guys, but this we come to the end of this video, and I hope you understood all the tools that I talked about. And if you guys have any queries regarding this session, please feel free to mention it in the comment section below till then. Thank you and happy learning. I hope you have enjoyed listening to this video. Please be kind enough to like it and you can comment any of your doubts and queries and we will reply them at the earliest. Do look out for more videos in our playlist and subscribe to any Rekha channel to learn more happy learning.