Course/Topic - Deep Learning with TensorFlow - all lectures

• 

  Class 1 - TensorFlow Introduction

  In this lecture session we learn about the introduction of tensorflow and also talk about tensorflow is the learning framework of machine learning and deep learning.

  • 19:19
• 

  Class 2 - TensorFlow Applications

  In this tutorial we learn that TensorFlow has significant use in voice recognition systems like Telecom, Mobile companies, security systems, search engines, etc. It uses the voice recognition systems for giving commands, performing operations and giving inputs without using keyboards, mouse.

  • 15:19
• 

  Class 3 - TensorFlow Basics - part 1

  In this lecture session we learn about Tensorflow basic functions and also talk about Tensorflow is basically a software library for numerical computation using data flow.

  • 17:13
• 

  Class 4 - TensorFlow Basics - part 2

  In this lecture session we learn about TensorFlow is a machine learning framework developed by Google Brain Team. It is derived from its core framework: Tensor. In TensorFlow, all the computations involve tensors. A tensor is a vector or a matrix of n-dimensions which represents the types of data.

  • 14:26
• 

  Class 5 - TensorFlow Components - part 1

  In this tutorial we learn about The TensorBoard enables us to monitor graphically and visually what TensorFlow is doing. Tensorflow’s name is directly derived from its core framework: Tensor. In Tensorflow, all the computations involve tensors. A tensor is a vector or matrix of n-dimensions that represents all types of data.

  • 19:32
• 

  Class 6 - TensorFlow Components - part 2

  In this lecture session we learn about In TensorFlow, all operations are conducted inside a graph. The group is a set of calculations that takes place successively. Each transaction is called an op node. TensorFlow makes use of a graph framework.

  • 17:32
• 

  Class 7 - TensorFlow Pipeline

  In this lecture session we learn about ensorFlow Extended (TFX) is an end-to-end platform for deploying production ML pipelines. When you’re ready to move your models from research to production, use TFX to create and manage a production pipeline.

  • 10:10
• 

  Class 8 - TensorFlow Examples

  In this lecture session we learn about In TensorFlow, codes are written to create a graph, run a session, and execute the graph. Every variable we assign becomes a node where we can perform mathematical operations such as multiplication and addition.

  • 19:40
• 

  Class 9 - Introduction to Linear Algebra - part 1

  In this lecture session we learn about Tensor algebra. In mathematics, the tensor algebra of a vector space V, denoted T(V) or T•(V), is the algebra of tensors on V (of any rank) with multiplication being the tensor product.

  • 33:06
• 

  Class 10 - Introduction to Linear Algebra - part 2

  In this lecture session we learn about Linear algebra is the study of linear combinations. It is the study of vector spaces, lines and planes, and some mappings that are required to perform the linear transformations. It includes vectors, matrices and linear functions.

  • 27:08
• 

  Class 11 - Introduction to Python - part 1

  In this lecture session we learn about Python. It is a very simple programming language so even if you are new to programming, you can learn python without facing any issues. Interesting fact: Python is named after the comedy television show Monty Python’s Flying Circus.

  • 13:55
• 

  Class 12 - Introduction to Python - part 2

  In this tutorial we learn about basic introduction to python programming and also talk about features and functions of python programming in brief.

  • 13:39
• 

  Class 13 - Introduction to Python - part 3

  In this lecture session we learn about Python is a popular programming language. It was created by Guido van Rossum, and released in 1991. It is used for: web development (server-side), software development, mathematics.

  • 11:20
• 

  Class 14 - Introduction to Python - part 4

  In this tutorial we learn about Functions that can be both built-in or user-defined. It helps the program to be concise, non-repetitive, and organized. We can create a Python function using the def keyword. After creating a function we can call it by using the name of the function followed by parenthesis containing parameters of that particular function.

  • 06:46
• 

  Class 15 - Introduction to Python - part 5

  In this tutorial we learn about There are the following advantages of Python functions. Using functions, we can avoid rewriting the same logic/code again and again in a program. We can call Python functions multiple times in a program and anywhere in a program. We can track a large Python program easily when it is divided into multiple functions.

  • 08:40
• 

  Class 16 - Introduction to Python - part 6

  In this tutorial we learn about The purpose is to make your code more manageable and extensible. In-built functions in Python are the in-built codes for direct use. For example, print () function prints the given object to the standard output device (screen) or to the text stream file. In Python 3.6 (latest version), there are 68 built-in functions.

  • 16:32
• 

  Class 17 - Introduction to Python - part 7

  In this lecture session we learn that These operators are used to perform similar operations as that of logical gates; there are 3 types of logical operators in python. Python Operators are the backbone of any operations and functions in the programming context. This has been a guide to Python Operators.

  • 22:12
• 

  Class 18 - Introduction to Python - part 8

  In this lecture session we learn about There are various compound operators in Python like a += 5 that adds to the variable and later assigns the same. It is equivalent to a = a + 5. Python language offers some special types of operators like the identity operator or the membership operator. They are described below with examples. is and is not are the identity operators in Python.

  • 18:39
• 

  Class 19 - Introduction to Python - part 9

  In this lecture session we learn about Functions that can be both built-in or user-defined. It helps the program to be concise, non-repetitive, and organized. We can create a Python function using the def keyword. After creating a function we can call it by using the name of the function followed by parenthesis containing parameters of that particular function.

  • 16:53
• 

  Class 20 - Introduction to Python - part 10

  In this lecture session we learn about When the function is called, we pass along a first name, which is used inside the function to print the full name: Arguments are often shortened to args in Python documentations.

  • 18:40
• 

  Class 21 - Introduction to Python - part 11

  In this tutorial we learn about There are 3 types of arguments that you'll most likely encounter while writing an argumentative essay. These are: 1. Classical Argument The classical or Aristotelian model of argument is the most common type of argument. It was developed by a Greek philosopher and rhetorician, Aristotle.

  • 10:36
• 

  Class 22 - Introduction to Python - part 12

  In this lecture session we learn about Variable type in Python: Data types are the classification or categorization of data items. It represents the kind of value that tells what operations can be performed on a particular data. Since everything is an object in Python programming, data types are actually classes and variables are instances (object) of these classes.

  • 06:37
• 

  Class 23 - Introduction to Python - part 13

  In this lecture session we learn about functions by calling the function with required arguments, without having to worry about how they actually work. There's a whole wealth of built-in functions in Python. In this post, we shall see how we can define and use our own functions.

  • 32:18
• 

  Class 24 - Introduction to Python - part 14

  In this lecture session we learn about how to find the number is prime or not and also talk about more examples of finding prime numbers

  • 20:48
• 

  Class 25 - Introduction to Python - part 15

  In this lecture session we learn about Num function in python programming and also talk about different functions in python in brief.

  • 17:05
• 

  Class 26 - Introduction to Matplotlib

  In this tutorial we learn about Matplotlib is a Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms. Matplotlib can be used in Python scripts, the Python and IPython shells, the Jupyter notebook, web application servers, and four graphical user interface toolkits.

  • 1:04:09
• 

  Class 27 - Introduction to NumPy - part 1

  In this tutorial we learn about the points that explain the advantages of NumPy: 1 The core of Numpy is its arrays. ... 2 Numpy supports some specific scientific functions such as linear algebra. ... 3 Numpy supports vectorized operations, like element wise addition and multiplication, computing Kronecker product, etc.

  • 24:43
• 

  Class 28 - Introduction to NumPy - part 2

  In this lecture session we learn about At the core of the NumPy package, is the ndarray object. This encapsulates n -dimensional arrays of homogeneous data types, with many operations being performed in compiled code for performance. There are several important differences between NumPy arrays and the standard Python sequences.

  • 29:55
• 

  Class 29 - Introduction to Pandas - part 1

  In this lecture session we learn about The Python library to do the mathematical operations in a flexible manner is called Pandas library. This is an open-source library used in data analysis and also in data manipulation so that data scientists can retrieve information from the data. It has a BSD license, and the number tables are manipulated easily.

  • 15:57
• 

  Class 30 - Introduction to Pandas - part 2

  In this lecture session we learn about Pandas DataFrame is two-dimensional size-mutable, potentially heterogeneous tabular data structure with labeled axes (rows and columns). A Data frame is a two-dimensional data structure.

  • 05:53
• 

  Class 31 - Introduction to Pandas - part 3

  In this tutorial we learn about Series is a one-dimensional labeled array capable of holding data of any type (integer, string, float, python objects, etc.). The axis labels are collectively called indexes. A pandas Series can be created using the following constructor.

  • 32:00
• 

  Class 32 - Introduction to Pandas - part 4

  In this lecture session we learn about Series is a one-dimensional, labeled data structure present in the Pandas library. The axis label is collectively known as index. Series structure can store any type of data such as integer, float, string, python objects, and so on.

  • 20:58
• 

  Class 33 - Introduction to Pandas - part 5

  In this lecture session we learn about Series is a one-dimensional labeled array capable of holding data of any type (integer, string, float, python objects, etc.). The axis labels are collectively called indexes.

  • 28:10
• 

  Class 34 - Introduction to Pandas - part 6

  In this tutorial we learn about String is an array of sequenced characters and is written inside single quotes, double quotes or triple quotes. Also, Python doesn’t have character data type, so when we write ‘a’, it is taken as a string with length 1.

  • 15:19
• 

  Class 35 - Introduction to Pandas - part 7

  In this lecture session we learn about Handling Missing Values in Python In this post, we will discuss: How to check for missing values Different methods to handle missing values Real life data sets often contain missing values. There is no single universally acceptable method to handle missing values.

  • 08:09
• 

  Class 36 - Introduction to Pandas - part 8

  In this lecture session we learn about The slice() function that returns a slice object. A slice object is used to specify how to slice a sequence. You can specify where to start the slicing, and where to end. You can also specify the step, which allows you to e.g. slice only every other item.

  • 18:57
• 

  Class 37 - File Management - part 1

  In this lecture session we learn that Python comes with functions that enable creating, opening, closing, reading, and writing files built-in. Opening a file in Python is as simple as using the open () function that is available in every Python version. The function returns a "file object.

  • 14:08
• 

  Class 38 - File Management - part 2

  In this lecture session we learn about We use the open () function in Python to open a file in read or write mode. As explained above, open () will return a file object. To return a file object we use open () function along with two arguments, that accepts filename and the mode, whether to read or write. So, the syntax being: open (filename, mode).

  • 23:38
• 

  Class 39 - File Management - part 3

  In this lecture session we learn about Before you can write to or read from a file, you must open the file first. To do this, you can use the open () function that comes built into Python. The function takes two arguments or parameters: one that accepts the file's name and another that saves the access mode. It returns a file object and has the following syntax.

  • 14:48
• 

  Class 40 - Machine Learning - part 1

  In this lecture session we learn about The Machine Learning process starts with inputting training data into the selected algorithm. Training data being known or unknown data to develop the final Machine Learning algorithm. The type of training data input does impact the algorithm, and that concept will be covered further momentarily.

  • 27:27
• 

  Class 41 - Machine Learning - part 2

  In this tutorial we learn Machine learning ( ML) is the study of computer algorithms that improve automatically through experience and by the use of data. It is seen as a part of artificial intelligence.

  • 17:31
• 

  Class 42 - Machine Learning - part 3

  In this lecture session we learn about In machine learning and pattern recognition, a feature is an individual measurable property or characteristic of a phenomenon being observed. Choosing informative, discriminating and independent features is a crucial step for effective algorithms in pattern recognition, classification and regression.

  • 17:36
• 

  Class 43 - Machine Learning - part 4

  In this lecture session we learn about machine language, the numeric codes for the operations that a particular computer can execute directly. The codes are strings of 0s and 1s, or binary digits(“bits”), which are frequently converted both from and to hexadecimal (base 16) for human viewing and modification.

  • 15:38
• 

  Class 44 - Machine Learning - part 5

  In this lecture session we learn that machine language is a collection of binary digits or bits that the computer reads and interprets. Machine language is the only language a computer is capable of understanding. The exact machine language for a program or action can differ by operating system.

  • 13:53
• 

  Class 45 - Machine Learning - part 6

  In this lecture session we learn about Machine language. Machine language, the numeric codes for the operations that a particular computer can execute directly. The codes are strings of 0s and 1s, or binary digits (“bits”), which are frequently converted both from and to hexadecimal (base 16) for human viewing and modification.

  • 11:55
• 

  Class 46 - Machine Learning - part 7

  In this lecture session we learn about the Machine learning life cycle is a cyclic process to build an efficient machine learning project. The main purpose of the life cycle is to find a solution to the problem or project.

  • 18:51
• 

  Class 47 - Machine Learning - part 8

  In this lecture we learn about In order to predict, you have to find a function (model) that best describes the dependency between the variables in our dataset. This is called training the model. The training dataset will be a subset of the entire dataset from the pandas data frame df that you created in part two of this series.

  • 23:55
• 

  Class 48 - Machine Learning - part 9

  In this lecture session we learn about why we need a data set in machine languages and also talk about some features and functions of a data set in machine language.

  • 22:38
• 

  Class 49 - Machine Learning - part 10

  In this lecture session we learn about Data preprocessing is required for cleaning the data and making it suitable for a machine learning model which also increases the accuracy and efficiency of a machine learning model. It involves the steps below.

  • 29:13
• 

  Class 50 - Machine Learning - part 11

  In this lecture session we learn about Machine learning (ML) is a subfield of artificial intelligence (AI) that allows computers to learn to perform tasks and improve performance over time without being explicitly programmed.

  • 08:08
• 

  Class 51 - Machine Learning - part 12

  In this lecture session we learn about 1 Supervised Learning. Supervised learning is when you provide the machine with a lot of training data to perform a specific task. 2 Unsupervised Learning. 3 Reinforcement Learning.

  • 35:11
• 

  Class 52 - Machine Learning - part 13

  In this lecture session we learn about Supervised Machine Learning is an algorithm that learns from labeled training data to help you predict outcomes for unforeseen data. In Supervised learning, you train the machine using data that is well “labeled.” It means some data is already tagged with correct answers.

  • 15:03
• 

  Class 53 - Machine Learning - part 14

  In this lecture session we learn about how we determine the type of training and also talk about the importance of types of machine learning language.

  • 16:18
• 

  Class 54 - Machine Learning - part 15

  In this lecture session we learn about regression analysis that helps one understand how the typical value of the dependent variable (or 'criterion variable') changes when any one of the independent variables is varied, while the other independent variables are held fixed.

  • 13:58
• 

  Class 55 - Machine Learning - part 16

  In this lecture session we learn about logistic regression is the statistical technique used to predict the relationship between the dependent variable (Y) and the independent variable (X), where the dependent variable is binary in nature. For example, the output can be Success/Failure, 0/1, True/False, or Yes/No.

  • 19:45
• 

  Class 56 - Machine Learning - part 17

  In this lecture session we learn about regression analyses, the logistic regression is a predictive analysis. Logistic regression is used to describe data and to explain the relationship between one dependent binary variable and one or more nominal, ordinal, interval or ratio-level independent variables.

  • 05:12
• 

  Class 57 - Machine Learning - part 18

  In this tutorial we learn about how we classify the implementation of machine learning and also talk about some more examples of implementation of machine learning.

  • 31:39
• 

  Class 58 - Machine Learning - part 19

  In this lecture session we learn about Linear regression is one of the easiest and most popular Machine Learning algorithms. It is a statistical method that is used for predictive analysis. Linear regression makes predictions for continuous/real or numeric variables such as sales, salary, age, product price, etc.

  • 28:19
• 

  Class 59 - Machine Learning - part 20

  In this lecture session we learn about A feature that is a measurable property of the object you’re trying to analyze. In datasets, features appear as columns: The image above contains a snippet of data from a public dataset with information about passengers on the ill-fated Titanic maiden voyage.

  • 17:36
• 

  Class 60 - Machine Learning - part 21

  In this lecture session we learn about basic examples of machine learning and also talk about more examples of machine learning.

  • 25:08
• 

  Class 61 - Machine Learning - part 22

  In this session we learn about developing the model in machine learning and also talk about different models and how we develop it in machine learning.

  • 31:56
• 

  Class 62 - TensorFlow Playground

  In this lecture session we learn about how TensorFlow Playground solves this particular problem. On the Playground, click the Play button in the upper left corner. The line between blue and orange data points begins to move slowly. Hit the reset button and click play again a few times to see how the line moves with different initial values.

  • 36:00
• 

  Class 63 - TensorFlow Perceptrons - part 1

  In this lecture session we learn about A Perceptron is an algorithm for supervised learning of binary classifiers. This algorithm enables neurons to learn and process elements in the training set one at a time.

  • 22:00
• 

  Class 64 - TensorFlow Perceptrons - part 2

  In this lecture session we learn about Multi-Layer perceptrons, define the most complicated architecture of artificial neural networks and also talk about functions of multilayer perceptrons.

  • 16:45
• 

  Class 65 - TensorFlow Perceptrons - part 3

  In this lecture session we learn about Single Layer Perceptrons. For understanding single layer perceptrons, it is important to understand Artificial Neural Networks (ANN). Artificial neural networks is the information processing system the mechanism of which is inspired by the functionality of biological neural circuits.

  • 12:00
• 

  Class 66 - TensorFlow and Artificial Intelligence

  In this lecture session we learn about Artificial Intelligence (AI) Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities of the human mind.

  • 19:39
• 

  Class 67 - ANN

  In this tutorial we learn about Artificial neural networks. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal from one artificial neuron to another.

  • 11:20
• 

  Class 68 - Types of ANN - part 1

  In this tutorial we learn that there are two types of ANN. Such as FeedForward and Feedback. a. FeedForward ANN In this network flow of information is unidirectional.here are two types of ANN. Such as FeedForward and Feedback. a. FeedForward ANN In this network flow of information is unidirectional.

  • 21:55
• 

  Class 69 - Types of ANN - part 2

  In this lecture session we learn about the structure of the ANN affected by a flow of information. Hence, neural network changes were based on input and output. Basically, we can consider ANN as nonlinear statistical data.

  • 17:10
• 

  Class 70 - Components of Neural Networks

  In this lecture session we learn about Artificial neural networks (ANNs) that consist of a node layer, containing an input layer, one or more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and has an associated weight and threshold.

  • 14:25
• 

  Class 71 - Classification in TensorFlow - part 1

  In this tutorial we learn about In order to build a model, it is recommended to have GPU support, or you may use the Google colab notebooks as well. Attention geek! Strengthen your foundations with the Python Programming Foundation Course and learn the basics.

  • 14:07
• 

  Class 72 - Classification in TensorFlow - part 2

  In this tutorial we learn that there are basically two classes- “≤50K” and “>50K. However, we can not leave our target labels in the current string format. This is because TensorFlow does not understand strings as labels.

  • 17:00
• 

  Class 73 - Classification in TensorFlow - part 3

  In this lecture session we learn about The data can be accessed at my GitHub profile in the TensorFlow repository. Here is the link to access the data. My code and Jupyter notebook can be accessed below.

  • 20:00
• 

  Class 74 - Classification in TensorFlow - part 4

  In this lecture session we learn about features of Tensorflow in deep learning and also talk about some functions and importance of Tensorflow in brief.

  • 25:00
• 

  Class 75 - Classification in TensorFlow - part 5

  In this tutorial we learn about The data can be accessed at my GitHub profile in the TensorFlow repository. Here is the link to access the data. My code and Jupyter notebook can be accessed below.

  • 30:25
• 

  Class 76 - Linear Regression in TensorFlow

  In this lecture session we learn about Linear regression strives to show the relationship between two variables by applying a linear equation to observed data.

  • 37:10
• 

  Class 77 - Difference between TensorFlow - PyTorch - Theano - Keras

  In this lecture session we learn about Keras used in prominent organizations like CERN, Yelp, Square or Google, Netflix, and Uber. Theano is a deep learning library developed by the Université de Montréal in 2007. Comparing Theano vs TensorFlow, it offers fast computation and can be run on both CPU and GPU. Theano has been developed to train deep neural network algorithms.

  • 21:30
• 

  Class 78 - Object Identification in TensorFlow

  In this lecture session we learn about TensorFlow Object Detection Object detection is a process of discovering real-world object detail in images or videos such as cars or bikes, TVs, flowers, and humans. It allows identification, localization, and identification of multiple objects within an image, giving us a better understanding of an image.

  • 08:10
• 

  Class 79 - Super Keyword - part 1

  In this tutorial we learn about The super keyword refers to the objects of immediate parent class. Before learning super keywords you must have the knowledge of inheritance in Java so that you can understand the examples given in this guide.

  • 21:00
• 

  Class 80 - Super Keyword - part 2

  In this tutorial we learn about The Blender is an open source 3D computer graphics software. With the help of Blender, we can do 3D visualizations such as still images, 3D animations, VFX shots, video editing and a lot of more cool stuff.

  • 32:40
• 

  Class 81 - Super Keyword - part 3

  In this lecture session we learn about features of super keywords and also talk about some functions and importance of super keywords in brief.

  • 18:00
• 

  Class 82 - CNN - part 1

  In this lecture session we learn about deep learning CNN models to train and test, each input image will pass it through a series of convolution layers with filters (Kernels), Pooling, fully connected layers (FC) and apply Softmax function to classify an object with probabilistic values between 0 and 1.

  • 16:00
• 

  Class 83 - CNN - part 2

  In this lecture session we learn about machine learning called deep learning, they're likely talking about neural networks. Neural networks are modeled after our brains.

  • 22:10
• 

  Class 84 - CNN - part 3

  In this lecture session we learn about In deep learning, a convolutional neural network ( CNN/ConvNet) is a class of deep neural networks, most commonly applied to analyze visual imagery.

  • 24:00
• 

  Class 85 - RNN - part 1

  In this lecture session we learn about An RNN (Recurrent Neural Network) is a type of artificial neural network that can process sequential data, recognize patterns and predict the final output.

  • 13:34
• 

  Class 86 - RNN - part 2

  In this lecture session we learn about how RNNs can gain more in-depth insight into a sequence and its context from such datasets to derive significant meaning and arrive at an accurate prediction as per the targeted problem at hand.

  • 17:03
• 

  Class 87 - RNN Time Series - part 1

  In this lecture session we learn that the Time series is dependent on the previous time, which means past values include significant information that the network can learn.

  • 29:41
• 

  Class 88 - RNN Time Series - part 2

  In this tutorial we learn about NNs containing recurrent layers that are designed to process sequences of inputs. You can feed in batches of sequences into RNNs and it will output a batch of forecasts after going through a dense layer.

  • 17:28
• 

  Class 89 - TensorBoard

  In these lecture sessions we learn about TensorFlow includes a visualization tool, which is called the TensorBoard. It is used for analyzing Data Flow Graph and also used to understand machine-learning models.

  • 11:00