![• Google’s TensorFlow is currently the most popular deep learning
library in the world
• Tensors are vectors or matrices of n dimensions.
a
m
k
q
d
Dimensions
2
4
8
1
1
9
3
2
5
4
4
6
6
3
3
7
8
2
9
5
[5] [5,4] [3,3,3]](https://image.slidesharecdn.com/deeplearningtutorial-190530064036/75/Deep-Learning-Tutorial-Deep-Learning-Tutorial-For-Beginners-What-Is-Deep-Learning-Simplilearn-80-2048.jpg)
Uploaded bySimplilearn
Deep Learning Tutorial | Deep Learning Tutorial For Beginners | What Is Deep Learning? | Simplilearn
The document discusses deep learning and neural networks. It begins by defining deep learning as a subfield of machine learning that is inspired by the structure and function of the brain. It then discusses how neural networks work, including how data is fed as input and passed through layers with weighted connections between neurons. The neurons perform operations like multiplying the weights and inputs, adding biases, and applying activation functions. The network is trained by comparing the predicted and actual outputs to calculate error and adjust the weights through backpropagation to reduce error. Deep learning platforms like TensorFlow, PyTorch, and Keras are also mentioned.
In this document
Powered by AI
Introduces deep learning, its applications, and its importance in predicting weather events. Deep learning applications include weather predictions, speech recognition, image recognition, and targeted advertising.
Deep learning is a subfield of machine learning focused on algorithms inspired by brain structure.Deep learning excels with unstructured data and complex operations, outperforming traditional machine learning.
Deep learning excels with unstructured data and complex operations, outperforming traditional machine learning.
Deep learning excels with unstructured data and complex operations, outperforming traditional machine learning.
Deep learning excels with unstructured data and complex operations, outperforming traditional machine learning.
Explains the basics of neural networks, where each neuron processes input to produce output.
Details operations within a neuron, involving inputs, weights, biases, and the activation function.
Discusses the cost function which evaluates prediction errors, guiding adjustments in neural networks.
Describes how neural networks are trained and how data flows through input and hidden layers.
Illustrates the step-by-step neuron activation process within hidden layers to generate outputs.
Focuses on the training process of networks, backpropagation, and achieving better prediction accuracy.
Discusses the cost function which evaluates prediction errors, guiding adjustments in neural networks.
Focuses on the training process of networks, backpropagation, and achieving better prediction accuracy.
Focuses on the training process of networks, backpropagation, and achieving better prediction accuracy.
Introduces various deep learning platforms like TensorFlow and Keras, highlighting their features.
Introduces various deep learning platforms like TensorFlow and Keras, highlighting their features.Highlights TensorFlow as a leading deep learning library, explaining tensors and workflow.
More Related Content
Similar to Deep Learning Tutorial | Deep Learning Tutorial For Beginners | What Is Deep Learning? | Simplilearn
More from Simplilearn
Deep Learning Tutorial | Deep Learning Tutorial For Beginners | What Is Deep Learning? | Simplilearn
- 2. What’s in itfor you? Cost function How do neural networks work? Deep learning platforms Introduction to TensorFlow Use case implementation using TensorFlow Applications of deep learning Why is deep learning important? Activation function What are neural networks? What is deep learning?
- 3. Applications of deeplearning
- 4. Deep learning helpsus make predictions about the rain, earthquakes, tsunamis etc, allowing us to take the required precautions
- 5. With deep learning,machines can comprehend speech and provide the required output
- 6. Deep learning enablesthe machine to recognize people and objects in the images fed to it
- 7. With deep learning,advertisers can leverage data to perform real-time bidding and targeted display advertising
- 8. What is deeplearning?
- 9. Deep learning isa subfield of machine learning that deals with algorithms inspired by the structure and function of the brain
- 10. Deep learning isa subfield of machine learning that deals with algorithms inspired by the structure and function of the brain Artificial Intelligence Machine Learning Deep Learning
- 11. Deep learning isa subfield of machine learning that deals with algorithms inspired by the structure and function of the brain Artificial Intelligence Machine Learning Deep Learning Ability of a machine to imitate intelligent human behavior
- 12. Deep learning isa subfield of machine learning that deals with algorithms inspired by the structure and function of the brain Artificial Intelligence Machine Learning Deep Learning Ability of a machine to imitate intelligent human behavior Application of AI that allows a system to automatically learn and improve from experience
- 13. Deep learning isa subfield of machine learning that deals with algorithms inspired by the structure and function of the brain Artificial Intelligence Machine Learning Deep Learning Ability of a machine to imitate intelligent human behavior Application of AI that allows a system to automatically learn and improve from experience Application of machine learning that uses complex algorithms and deep neural nets to train a model
- 14. Why is deeplearning important?
- 15. Works with unstructureddata Machine learning works only with large sets of structured and semi-structured data, while deep learning can work with both structured and unstructured data
- 17. Handles complex operations Deeplearning algorithms can perform complex operations easily while machine learning algorithms cannot
- 19. Feature Extraction Machine learningalgorithms use labeled sample data to extract patterns, while deep learning accepts large volumes of data as input, analyze the input to extract features out of an object
- 21. Achieve best performance Performanceof machine learning algorithms decreases as the amount of data increase, so to maintain the performance of the model we need deep learning
- 22. What are neuralnetworks?
- 23. Square With deep learning,a machine can be trained to identify various shapes
- 24. Square With deep learning,a machine can be trained to identify various shapes
- 25. Square With deep learning,a machine can be trained to identify various shapes But, how is the machine able to do this?
- 26. Square With deep learning,a machine can be trained to identify various shapes With neural networks of course!
- 27. A neural networkis a system modeled on the human brain inputs outputneuron
- 28. The data isfed as input to the neuron inputs outputneuron
- 29. The neuron processesthe information provided as input inputs outputneuron
- 30. The information istransferred over weighted channels inputs outputneuron
- 31. The output isthe final value predicted by the artificial neuron inputs outputneuron
- 32. But what exactlyhappens within a neuron? Note to instructor: Let’s first go through a few concepts that help us understand neural networks
- 33.
- 35. Within each neuronthe following operations are performed: • The product of each input and the weight of the channel it’s passed over is found outputneuron x 1 x2 x3 x4 inputs
- 36. Within each neuronthe following operations are performed: • The product of each input and the weight of the channel it’s passed over is found • Sum of the weighted products is computed. This is called the weighted sum inputs outputneuron x 1 x2 x3 x4 x1*w1 + x2*w2 + x3*w3 + x4*w4
- 37. Within each neuronthe following operations are performed: • The product of each input and the weight of the channel it’s passed over is found • Sum of the weighted products is computed. This is called the weighted sum • Bias unique to the neuron is added to the weighted sum inputs outputneuron x 1 x2 x3 x4 x1*w1 + x2*w2 + x3*w3 + x4*w4 + bias
- 38. Within each neuronthe following operations are performed: • The product of each input and the weight of the channel it’s passed over is found • Sum of the weighted products is computed. This is called the weighted sum • Bias unique to the neuron is added to the weighted sum • The final sum is then subjected to a particular function known as the activation function inputs output x 1 x2 x3 x4 x1*w1 + x2*w2 + x3*w3 + x4*w4 + bias final sum Activation function ( final sum)
- 39.
- 40. inputs predicted output x 1 x2 x3 x4 neuron y^ TheCost value is the difference between the neural nets predicted output and the actual output from a set of labeled training data y actual output
- 41. inputs predicted output x 1 x2 x3 x4 neuron y^ TheCost value is the difference between the neural nets predicted output and the actual output from a set of labeled training data The least cost value is obtained by making adjustments to the weights and biases iteratively throughout the training process y actual output
- 42. Let’s learn howneural networks work
- 43. How do neuralnetworks work?
- 44. Our neural networkwill be trained to identify shapes
- 45. 28 28 28*28=784 Our shapes areimages of 28*28 pixels
- 46. 28 28 28*28=784 Each pixel isfed as input to the neurons in the first layer
- 47. Each pixel isfed as input to the neurons in the first layer Input layer x1 x2 xn
- 48. Hidden layers improvethe accuracy of the output Input layer Hidden layers x1 x2 xn
- 49. Data is passedon from layer to layer over weighted channels Input layer Hidden layers w1 w2 w3 wm x1 x2 xn
- 50. Each neuron inthe first hidden layer takes a subset of the inputs and processes it Input layer Hidden layers w1 w2 w3 wm b1 b2 b3 b4 b5 x1 x2 xn
- 51. Each neuron inthe first hidden layer takes a subset of the inputs and processes it Input layer Hidden layers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Let’s look into what happens within the neurons
- 52. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Step 1: x1*w1 + x2*w2 + b1 Step 2: Φ(x1* w1 + x2*w2 + b1) where Φ is an activation function
- 53. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Step 1: x1*w1 + x2*w2 + b1 Step 2: Φ(x1* w1 + x2*w2 + b1) where Φ is an activation function The results of the activation function determine which neurons will be activated in the following layer
- 54. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn The results of the activation function determine which neurons will be activated in the following layer w11 w1 2 w1n b1 1 b12 b13 b14 b15
- 55. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn w11 w1 2 w1n b1 1 b12 b13 b14 b15 The results of the activation function determine which neurons will be activated in the following layer
- 56. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Just as before, the information reaching this layer is processed after which a single neuron in the output layer gets activated w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n w2k
- 57. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Just as before, the information reaching this layer is processed after which a single neuron in the output layer gets activated w11 w1 2 w1m b1 1 b12 b13 b14 b15 w2 1 w2m square circle triangle But, our input was a square! What went wrong here?
- 58. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn Just as before, the information reaching this layer is processed after which a single neuron in the output layer gets activated w11 w1 2 w1m b1 1 b12 b13 b14 b15 w2 1 w2m square circle triangle Well, our network needs to be trained first
- 59. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn The predicted output is compared against the actual output by calculating the cost function w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n w2k
- 60. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y The most commonly used cost function is as follows: C=1/2(Y-Y)2^ where Y is the actual value and Y is the predicted value ^ w1n w2k
- 61. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn The cost function determines the error in prediction and reports it back to the neural network w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n w2k
- 62. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 wm x1 x2 xn This is called backpropagation w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n w2k
- 63. Input layer Hiddenlayers w1 ’ w2’ w3’ b1 b2 b3 b4 b5 wm’ x1 x2 xn The weights are adjusted in order to reduce the error w11 ’ w12 ’ w1n’ b1 1 b12 b13 b14 b15 w21’ w2k’ square circle triangle ^y
- 64. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn The network is trained with the new weights w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle^y w1n’ w2k’ wm’
- 65. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’ ^y C=1/2(Y-Y)2^ Once again, the cost is determined and back propagation is continued until the cost cannot be reduced any further
- 66. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’
- 67. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n’ w2k’ wm’ Similarly, our network must be trained to identify circles and triangles too
- 68. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle ^y w1n’ w2k’ wm’ The weights are thus further adjusted in order to predict the three shapes with the highest accuracy
- 69. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’ We can now rely on our neural network to predict the input shapes 28 28 28*28=784
- 70. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’ We can now rely on our neural network to predict the input shapes 28 28 28*28=784
- 71. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’ We can now rely on our neural network to predict the input shapes 28 28 28*28=784
- 72. Input layer Hiddenlayers w1 w2 w3 b1 b2 b3 b4 b5 x1 x2 xn w11 w1 2 b1 1 b12 b13 b14 b15 w2 1 square circle triangle w1n’ w2k’ wm’ We can now rely on our neural network to predict the input shapes 28 28 28*28=784
- 73.
- 74. The primary programminglanguage is LUA with an implementation in C too. Torch’s Python implementation is called PyTorch
- 75. Keras is aPython framework for deep learning. Its USP is reusability of code for CPU and GPU
- 76. TensorFlow is adeep learning platform by Google. It is developed in C++ and has its implementation is Python
- 77. DL4J is thefirst deep learning library written for Java and Scala. It is integrated with Hadoop and Apache Spark
- 78.
- 79. • Google’s TensorFlowis currently the most popular deep learning library in the world
- 80. • Google’s TensorFlowis currently the most popular deep learning library in the world • Tensors are vectors or matrices of n dimensions. a m k q d Dimensions 2 4 8 1 1 9 3 2 5 4 4 6 6 3 3 7 8 2 9 5 [5] [5,4] [3,3,3]
- 81. • Google’s TensorFlowis currently the most popular deep learning library in the world • Tensors are vectors or matrices of n dimensions. • In TensorFlow, all computations performed involve tensors
- 82. • Google’s TensorFlowis currently the most popular deep learning library in the world • Tensors are vectors or matrices of n dimensions. • In TensorFlow, all computations performed involve tensors • TensorFlow architecture is as follows Pre-processing data Build a model Train and estimate the model
- 83. Use case implementationwith TensorFlow
Editor's Notes
- #3 Style - 01