Understanding computer vision with Deep Learning
1 like1,623 views
The document discusses the features and functionalities of CloudxLab, an AI-enabled ed-tech platform aimed at addressing the skill gaps in emerging technologies through gamified learning and personalized content. It details the components of machine learning and computer vision, including gradient descent, neural networks, and the importance of practice and instant feedback in the learning process. Additionally, user testimonials highlight the platform's effectiveness in providing access to powerful computing resources and collaborative learning tools.
![Example Face Embedding
Facenet
Facenet
Facenet
Facenet
[0.3, -0.1, 0.3, …… 128 numbers]
[0.2, 0.1, 0.8, …… 128 numbers]
[0.1, 0.2, 0.6, …… 128 numbers]
[0.8, 0.9, 0.3, …… 128 numbers]
Facenet
[0.2, -0.1, 0.3, …… 128 numbers]](https://image.slidesharecdn.com/understandingworkingofmachinelearningcnncomputervision-191017065229/85/Understanding-computer-vision-with-Deep-Learning-184-320.jpg)
![Example Face Embedding
Facenet
Facenet
Facenet
Facenet
[0.3, -0.1, 0.3, …… 128 numbers]
[0.2, 0.1, 0.8, …… 128 numbers]
[0.1, 0.2, 0.6, …… 128 numbers]
[0.8, 0.9, 0.3, …… 128 numbers]
Facenet
[0.2, -0.1, 0.3, …… 128 numbers]](https://image.slidesharecdn.com/understandingworkingofmachinelearningcnncomputervision-191017065229/85/Understanding-computer-vision-with-Deep-Learning-185-320.jpg)
Understanding computer vision with Deep Learning
- 2. Agenda ● About CloudxLab ● About Speaker ● Intro to Machine Learning ● Gradient Descent & Back Propagation ● Neural networks & CNN ● Computer Vision ● GANs ● Face Embedding
- 3. CloudxLab.com AI enabled Ed-Tech platform solving the skill-gap in emerging technologies.
- 4. CloudxLab.com Learning can be hard without the right tools, especially Deep Tech The Problem Plethora of content but not engaging enough The instant feedback is not available Content alone in not sufficient. Need Practice. One course doesn’t fit all. Every user is different
- 5. CloudxLab.com How are we solving it? Gamified Learning Environment Knowledge Graph To engage you and your peers for collaborative learning To identify gaps, and strengths, and to improve learning curve
- 6. CloudxLab.com Gamified Learning Environment BootMLTM - Build machine learning models on the fly. Auto Assessment Engine Online Lab - Playground Hooks - Concept Wise Discussion, XP Points, Forum, Leaderboard Auto Quiz, Slides Finder in Videos Best in class content User Behavioural Analytics
- 7. CloudxLab.com Online Lab - Playground Everything available on Cloud. Zero installation - Get started instantaneously. Real Experience - Real Learning Access from anywhere, anytime 24x7. Shared Datasets and Quick to Debug Very easy to integrate into any LMS Online Lab - PlaygroundAI Powered gamified environment
- 8. CloudxLab.com Online Lab - PlaygroundAI Powered gamified environment Technologies available on Cloud Every open source tool - AI & Big Data
- 9. CloudxLab.com Auto Assessment EngineAI Powered gamified environment
- 10. CloudxLab.com Auto Assessment EngineAI Powered gamified environment
- 11. CloudxLab.com Best In Class ContentAI Powered gamified environment
- 12. CloudxLab.com Social Hooks: JobsAI Powered gamified environment
- 13. CloudxLab.com Social Hooks: JobsAI Powered gamified environment
- 14. CloudxLab.com Social Hooks: ForumAI Powered gamified environment
- 15. CloudxLab.com BootML - build machine learning models on the fly.AI Powered gamified environment
- 16. CloudxLab.com How are we solving it? With what minimal learning can users get maximum returns? Optimized Algorithm to help users figure out their current knowledge level Knowledge Graph Individual’s skill Graph Job skill graph ?
- 17. CloudxLab.com Real / Relavent / Practical Learning Engagement / Completion Rate Competitors Map University Courses Classroom Learning
- 18. What our Users say ...And a 100+ such reviews
- 19. Feedback on Lab from Users Been working with a startup from another ex-Amazonian: CloudxLab. Provides a learning environment for big data processing on a real cluster, that you can access via a web browser. Neat stuff. Frank Kane , Top Udemy Instructor Am using cloudxlab for more than an year. The main advantage of using cloudxlab, a) Get 6 node production cluster with all installed components, just getting user and password, you can start working on it. b) You have almost all the access... continue reading Sachin Peedikakkandy , Sr Engineer at DXC Technology We took CloudxLab to train our team on big data analytics and when we saw how much easier it was to use it than set up our own infrastructure. Almost like plug-n-play. IBM Blue Team , IBM India (70,000+ Users)
- 20. Feedback on Course from Users
- 21. Learners from top US Universities (And many more...)
- 22. Corporates
- 23. About Me Sandeep Giri Worked On Large Scale Computing Graduated from IIT Roorkee Software Engineer Love Explaining Technologies Founder Feel free to add me on linkedin
- 24. Computer Vision is everywhere
- 27. What is Machine Learning?
- 29. What is Machine Learning?
- 32. Question What will you do to make this program learn any other games such as PacMan ? Option 1 - Write new rules as per the game Option 2 - Just hook it to new game and let it play for a while
- 33. Question What will you do to make this program learn any other games such as PacMan ? Option 1 - Write new rules as per the game Option 2 - Just hook it to new game and let it play for a while
- 34. What is Deep Learning?
- 35. Nature has inspired many inventions
- 36. Inspiration from animal brains to achieve intelligence
- 37. How does machine learn?
- 38. Typical ML Process > Training AlgorithmData Model
- 39. AlgorithmData Model Live Data Prediction Typical ML Process > Predictions
- 40. Typical ML Process > Model and Algorithm AlgorithmData Model Live Data Prediction
- 41. Predicting salary based on the number of years of experience
- 44. 2000, 4000, 6000 Predicting Salary
- 45. 2000, 4000, 6000, ______ Predicting Salary
- 46. 2000, 4000, 6000, 8000 Predicting Salary
- 47. Years of Experience Salary 1 2000 2 4000 3 6000 Historical Data Let's formulate the machine learning problem.. Predicting Salary
- 48. Years of Experience Salary 1 2000 2 4000 3 6000 Model Historical Data Let's formulate the machine learning problem.. Training Predicting Salary
- 49. Years of Experience Salary 1 2000 2 4000 3 6000 Years of Experience Salary 4 ??? Model Historical Data Unknown Salary Let's formulate the machine learning problem.. Training Predicting Salary
- 50. Years of Experience Salary 1 2000 2 4000 3 6000 Years of Experience Salary 4 ??? Model Years of Experience Salary 4 8000 Historical Data Unknown Salary Prediction Let's formulate the machine learning problem.. Training Predicting Salary
- 51. Predicting Salary 1 2 3 2000 4000 6000 How would a computer do it? - plot it → Years Salary
- 52. Predicting Salary 1 2 3 2000 4000 6000 How would a computer do it? - plot it → Years Salary
- 53. Predicting Salary 1 2 3 2000 4000 6000 How would a computer do it? - plot it → Years Salary
- 54. Predicting Salary 1 2 3 2000 4000 6000 How would a computer do it? - plot it → Years Salary
- 55. Predicting Salary 1 2 3 2000 4000 6000 How would a computer do it? - plot it → Years Salary
- 56. 1 2 3 2000 4000 6000 4 Ask the plot for the salary in 4th yr! Predicting Salary → Years Salary
- 57. Predicting Salary 1 2 3 2000 4000 6000 8000 4 It is correct! → Years Salary
- 58. 1 2 3 2010 3980 6020 Life isn't perfect! You never get straight line! Predicting Salary
- 59. 2010 3980 6020 Linear Regression - Find best fitting line 1 2 3Predicting Salary
- 60. 2010 3980 6020 Line 1 Line 2 Line 3 Normal Equation - Mathematically Predicting Salary 1 2 3
- 61. Line 1Try multiple lines! Whichever is closer. 2010 3980 6020 Line 2 Line 3 Predicting Salary 1 2 3
- 62. Gradient Descent
- 63. 1 2 3 4 2010 3980 6020 Initial Guess Gradient Descent - A little greedy approach. Gradient Descent
- 64. 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Gradient Descent - find impact of slight change Gradient Descent
- 65. 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Gradient Descent - guess next line! Next line Gradient Descent
- 66. Gradient Descent Increase in slope is proportional to Rate of decrease of error w.r.t change in slope Gradient Descent 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Next line
- 67. Gradient Descent Increase in slope = learning rate * Rate of decrease of error wrt change in slope Some constant. Gradient Descent 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Next line
- 68. 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Next line Gradient Descent New Slope = Old Slope + Learning Rate * Rate of decrease of error wrt change in slope Gradient Descent
- 69. 1 2 3 4 2010 3980 6020 Initial Guess Try Increasing the slope a little bit Next line What if error increased due to increasing slope? Gradient Descent
- 70. Start with random line Gradient Descent Gradient Descent > Flowchart
- 71. Increase the slope a bit & Calculate change in error Start with random line Did the error decrease? Gradient Descent Gradient Descent > Flowchart
- 72. Increase the slope a bit & Calculate change in error Start with random line Did the error decrease? Increase the slope. Yes Gradient Descent Gradient Descent > Flowchart
- 73. Increase the slope a bit & Calculate change in error Start with random line Did the error decrease? Decrease the slope. No. Error increased Increase the slope. Yes Gradient Descent Gradient Descent > Flowchart
- 74. Increase the slope a bit & Calculate change in error Start with random line Did the error decrease? Decrease the slope. Stop, you have found the best line No. Error increased Increase the slope. Yes No, Error didn't change Gradient Descent Gradient Descent > Flowchart
- 75. Increase the slope a bit & Calculate change in error Start with random line Did the error decrease? Decrease the slope. Stop, you have found the best line No. Error increased Increase the slope. Yes No, Error didn't change Next epoch / iterationNext epoch / iteration Gradient Descent Gradient Descent > Flowchart
- 76. Gradient Descent Gradient Descent > Tap Analogy
- 77. Gradient Descent Gradient Descent > Tap Analogy
- 78. Gradient Descent Gradient Descent > Tap Analogy
- 79. Gradient Descent New Position Gradient Descent > Tap Analogy
- 80. Gradient Descent Begin Again! Gradient Descent > Tap Analogy
- 81. Gradient Descent New Position Slight right twist Gradient Descent > Tap Analogy
- 82. What if we had two knob? Comfortable position Gradient Descent > Tap Analogy
- 83. What if we had two knob? Gradient Descent > Two Knobs
- 84. Gradient Descent Gradient Descent > Two Knobs
- 85. Hot Cold Good Flow Right Temperature ModelInput Output Gradient Descent > Model Weights
- 86. What if we had more input features? Hot Cold Good Flow Right Temperature Country Gender Climate Gradient Descent > Model Model Weights Input Output
- 87. Deep Learning - Artificial Neural Network(ANN) Computing systems inspired by the biological neural networks that constitute animal brains. Deep Learning > Artificial Neural Network (ANN)
- 88. Multiple layers of neurons Deep Learning > Simple Neural Network (ANN) > Deep Learning Neural Network (DNN)
- 89. Multiple layers of neurons Deep Learning > Simple Neural Network (ANN) > Deep Learning Neural Network (DNN)
- 90. Multiple layers of neurons Deep Learning > Simple Neural Network (ANN) > Deep Learning Neural Network (DNN)
- 91. Multiple layers of neurons Deep Learning > Simple Neural Network (ANN) > Deep Learning Neural Network (DNN)
- 92. What if we had more input features? Hot Cold Good Flow Right Temperature Model Weights Input Output Country Gender Climate Deep Learning > Simple Neural Network (ANN)
- 93. We could improve the model further... Hot Cold Good Flow Right Temperature ModelInput Output Country Gender Climate Deep Learning > Deep Learning Neural Network (DNN)
- 94. And further…. Deep Neural Network... Hot Cold Good Flow Right Temperature Neural NetworkInput layer Output layer Country Gender Climate Deep Learning > Deep Learning Neural Network (DNN)
- 95. Training Neural Networks - Single Neuron Hot Cold Right Temperature Deep Learning > Training Neural Network
- 96. Training Neural Networks - How? Hot Cold Right Temperature Deep Learning > Training Neural Network
- 97. Training Neural Networks - How? Backpropagation - Two neuron Hot Cold Right Temperature First Knob Second Knob Deep Learning > Training Neural Network > Backpropagation
- 98. Training Neural Networks - Backpropagation Hot Cold Right Temperature 1. Initialisation First Knob Second Knob Deep Learning > Training Neural Network > Backpropagation
- 99. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? 2. Forward Pass Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 100. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? 3. Reverse Pass - Tweak Second knob. Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 101. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? 3. Reverse Pass - Tweak first knob. Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 102. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? 4. Reverse Pass - Tweak first knob. Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 103. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? 4. Reverse Pass - Tweak first knob. Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 104. Training Neural Networks - Backpropagation Hot Cold Right Temperature ?? Back to 1. Forward Pass - Take next instance Interim temperature Deep Learning > Training Neural Network > Backpropagation
- 105. Artificial Neuron - Let's get real! Deep Learning > Artificial Neuron
- 106. Artificial Neuron - Let's get real! Input Neuron Connection weight Output Deep Learning > Artificial Neuron
- 107. Artificial Neuron - Let's get real! bias Deep Learning > Artificial Neuron Input Neuron Connection weight Output
- 108. Artificial Neuron - Let's get real! Output = Input * weight + bias Deep Learning > Artificial Neuron > Weight and Bias bias Input Neuron Connection weight Output
- 109. Artificial Neuron - Let's get real! Output = Input * weight + bias Deep Learning > Artificial Neuron > Weight and Bias bias Input Neuron Connection weight Output
- 110. Artificial Neuron - Let's get real! Input1 Neuron bias Output Input2 Connection Weight 2 Connection Weight 1 Deep Learning > Artificial Neuron
- 111. Artificial Neuron - Let's get real! Output = Input1 * weight1 + input2 * weight2 + bias Deep Learning > Artificial Neuron Input1 Neuron bias Output Input2 Connection Weight 2 Connection Weight 1
- 112. Artificial Neuron - Let's get real! Input1 Neuron bias Connection weight Input2 Connection weight Activation function If value is too low, gives 0. Output Deep Learning > Artificial Neuron
- 113. Artificial Neuron - Let's get real! Input1 Neuron bias Connection weight Output Activation function If value is too low, gives 0.Input2 Connection weight Deep Learning > Artificial Neuron
- 114. Artificial Neuron - To make it like a electric circuit Input1 Neuron bias Connection weight Output Input2 Connection weight Deep Learning > Artificial Neuron
- 115. Artificial Neuron - To make it like a electric circuit Input1 Neuron bias Connection weight Output Input2 Connection weight Deep Learning > Artificial Neuron
- 116. Backpropagation with example Training a network based on years of work experience as input and Salary as output Deep Learning > Artificial Neuron > Backpropagation
- 117. EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Deep Learning > Artificial Neuron > Backpropagation Training a network based on years of work experience as input and Salary as output
- 118. First Second ? ? ? ? actual value Epoch 1 Record 1 EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Deep Learning > Artificial Neuron > Backpropagation
- 119. 1.0 4 Initialize with random weights or knobs. 50 0.1 30 actual value 100 EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 120. Two Neurons - 4 knobs. Take first record... ? 4 ? ? ? EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 actual value 100 Deep Learning > Artificial Neuron > Backpropagation
- 121. 1.0 4 Do the forward pass 50 0.1 30 54 4*1.0 + 50 EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 actual value 100 Deep Learning > Artificial Neuron > Backpropagation
- 122. 1.0 4 Do the forward pass 50 0.1 30 actual value 10035.454 Compute d value 54*0.1 + 30 EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 123. 1.0 4 Compute the error 50 0.1 30 actual value 10035.454 Computed value { || 100 - 35.4 || EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 124. 1.0 4 50 0.2 50 actual value 10035.454 Computed value Back Pass: Tweak the knob of the second neuron EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 125. 2.0 4 40 0.2 50 actual value 10035.454 Computed value Back Pass: Freeze the second knob, tweak the knob of the first neuron EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 126. Next Record. Repeat the process, Tweak the weights... 2.0 5 40 0.2 50 actual value 13050 55 Computed value EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 2 Deep Learning > Artificial Neuron > Backpropagation
- 127. Next Record. Repeat the process, Tweak the weights... 3.0 2 45 0.25 55 actual value 3051 67.75 Computed value Epoch 1 Record 3 EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Deep Learning > Artificial Neuron > Backpropagation
- 128. Next Record. Repeat the process, Tweak the weights... 3.5 5 47 0.2 40 actual value 14064.5 65.2 Computed value EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 1 Record 4 Deep Learning > Artificial Neuron > Backpropagation
- 129. Next Epoch. Begin again from the first record ... 4.0 4 51 0.21 41 actual value 10067 54.07 Computed value EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 2 Record 1 Deep Learning > Artificial Neuron > Backpropagation
- 130. Epoch #2 , Second Record, and so on. 5.0 5 50 0.1 45 actual value 13075 52.5 Computed value EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 Epoch 2 Record 2 Deep Learning > Artificial Neuron > Backpropagation
- 131. Once it has been trained, it is ready to do the predictions 4.75 6 42.25 0.215 43.12 ??? Predicted value EMP Work Ex Salary emp1 4 100 emp2 5 130 emp3 2 30 emp4 5 140 emp5 6 ?? Deep Learning > Artificial Neuron > Backpropagation
- 132. MNIST - classifying a handwritten image into 10 labels. ANN or Fully connected Neural Network 0 1 2 3 4 5 6 7 8 9 Labels Deep Learning > Artificial Neuron > ANN
- 133. It would basically compute probabilities of various digits Training Neural Network - MNIST .001 .001 0.04 0.06 0.03 0.1 0.07 0.01 0.6 0.07 Probabilities 0 1 2 3 4 5 6 7 8 9 Labels Deep Learning > Artificial Neuron > ANN
- 134. Training Neural Network - MNIST How to train it? .001 .001 0.04 0.06 0.03 0.1 0.07 0.01 0.6 0.07 Probabilities Deep Learning > Artificial Neuron > ANN
- 135. Step 1 - Initialize the weights ANN or Fully connected Neural Network Actual 0 1 2 3 4 5 6 7 8 9 Labels 0 0 0 0 0 0 0 0 1 0 Deep Learning > Artificial Neuron > ANN
- 136. Training Neural Network - MNIST Take an instance from training data. Actual Labels 0 1 2 3 4 5 6 7 8 9 0 0 0 0 0 0 0 0 1 0 Deep Learning > Artificial Neuron > ANN
- 137. Step 2 - Forward pass ANN or Fully connected Neural Network Labels Intermediate values Actual 0 1 2 3 4 5 6 7 8 9 0 0 0 0 0 0 0 0 1 0 Deep Learning > Artificial Neuron > ANN
- 138. ANN or Fully connected Neural Network Step 2 - Forward pass 0 1 2 3 4 5 6 7 8 9 0 0 0 0 0 0 0 0 1 0 Actual Labels Deep Learning > Artificial Neuron > ANN
- 139. Step 2 - Forward pass Actual Labels .1 .1 0.05 0.15 0.11 0.99 0.1 0.18 0.02 0.1 Computed ANN or Fully connected Neural Network 0 0 0 0 0 0 0 0 1 0 0 1 2 3 4 5 6 7 8 9 Deep Learning > Artificial Neuron > ANN
- 140. ANN or Fully connected Neural Network Step 2 - Forward pass Actual Labels .1 .1 0.05 0.15 0.11 0.99 0.1 0.18 0.02 Computed 0 0 0 0 0 0 0 0 1 0 0 1 2 3 4 5 6 7 8 90.1 Deep Learning > Artificial Neuron > ANN
- 141. ANN or Fully connected Neural Network Step 3 - Back Pass - Second Layer Frozen Layer 0.1 Actual Labels .1 .1 0.05 0.15 0.11 0.99 0.1 0.18 0.02 Computed 0 0 0 0 0 0 0 0 1 0 0 1 2 3 4 5 6 7 8 9 Deep Learning > Artificial Neuron > ANN
- 142. Training Neural Network - MNIST .1 .1 0.05 0.15 0.11 0.99 0.1 0.18 0.02 0.1 Predicted Frozen Layer Step 2 - Forward pass Actual Labels 0 0 0 0 0 0 0 0 1 0 0 1 2 3 4 5 6 7 8 9 Deep Learning > Artificial Neuron > ANN > Training
- 143. Pick next instance Training Neural Network - MNIST .45 .01 0.03 0.25 0.01 0.03 0.02 0.1 0.01 0.1 Predicted Actual Labels 1 0 0 0 0 0 0 0 0 0 0 1 2 3 4 5 6 7 8 9 Deep Learning > Artificial Neuron > ANN > Training
- 144. Next Iteration or epoch Training Neural Network - MNIST .1 .1 0.05 0.15 0.11 0.99 0.1 0.18 0.02 0.1 Predicted 0 0 0 0 0 0 0 0 1 0 Actual Deep Learning > Artificial Neuron > ANN > Training
- 145. Male Female This will require a lot of computing power Layers of neurons 10,000 pixels Output layer 100x100 3 layers each with 10000 weights and 2 last Total connections: 10000x10000 + 10000x10000 + 10000x2 ~ 200 million CNN > Fully Connected Network vs CNN
- 146. Male Female This will require a lot of computing power Layers of neurons 10,000 pixels Output layer 100x100 CNN > Fully Connected Network vs CNN Also notice that the adjacent pixels at 0,0 and 1,1 would go far away.
- 147. CNNs solve this problem by using partially connected layers called Convolutional Layers CNN > Fully Connected Network vs CNN
- 148. CNN > Convolutional Layer ● Neurons in the first convolutional layer are connected only to pixels in their receptive fields. Convolutional Layer
- 149. CNN > Convolutional Layer ● Neurons in the first convolutional layer are connected only to pixels in their receptive fields. Receptive Field Convolutional Layer
- 150. CNN > Convolutional Layer Convolutional Layer ● Neurons in the first convolutional layer are connected only to pixels in their receptive fields. ● Each neuron in the second convolutional layer is connected only to neurons located within a small rectangle in the first layer Receptive Field
- 151. CNN > Convolutional Layer Convolutional Layer ● The network concentrates on low-level features in the first hidden layer Receptive Field
- 152. CNN > Convolutional Layer Convolutional Layer ● The network concentrates on low-level features in the first hidden layer ● Then assemble them into higher-level features in the next hidden layer and so on. Receptive Field
- 153. CNN > Convolutional Layer Convolutional Layer ● The network concentrates on low-level features in the first hidden layer ● Then assemble them into higher-level features in the next hidden layer and so on. ● This hierarchical structure is common in real-world images Receptive Field
- 154. CNN > Convolutional Layer
- 155. CNN > Convolutional Layer
- 156. CNN > Convolutional Layer Input Layer This figure shows how the layers of CNN are formed
- 157. CNN > Convolutional Layer Input Layer Convolutional Layer This figure shows how the layers of CNN are formed
- 158. This figure shows how the layers of CNN are formed CNN > Convolutional Layer Input Layer Convolutional Layer Receptive Field
- 159. CNN > Convolutional Layer This figure shows how the layers of CNN are formed Input Layer Convolutional Layer
- 160. CNN > Convolutional Layer 0 1 0 0 1 0 0 1 0 0 0 0 1 1 1 0 0 0 Vertical Filter Horizontal Filter This figure shows how the layers of CNN are formed Convolutional Layer Input Layer
- 161. CNN > Pooling Layers Input Image Shrinked Image Pooling Layers
- 162. CNN > Pooling Layers Pooling Layers ● Computes the maximum value of the receptive field - Max pool
- 163. CNN > Pooling Layers Pooling Layers ● Computes the maximum value of the receptive field - Max pool ● Computes the average of all pixels - Average pool
- 165. The Image Classification Challenge: 1,000 object classes 1,431,167 images
- 166. Progress so far Russakovsky et al. IJCV 2015
- 167. Problems related to image classification ...
- 168. A typical CNN..
- 169. How AI works in it? Various Computer Vision Task
- 170. How AI works in it? Sliding Window
- 171. R-CNN < Fast R-CNN < Faster R-CNN < Mask R-CNN < YOLO < YOLO v3
- 172. How AI works in it? YOLO v3 (You Only Look Once) Fastest object detection algorithm Deep CNN Intersection over Union Bounding Box Detection
- 173. Yolo v3 - Deep CNN More at: https://pjreddie.com/media/files/papers/YOLOv3.pdf
- 175. What? ● In a conference like this ● we want to live stream and record it. ● But the presenter gets out of focus as she/he moves ● Automating the cameraman is the only option! ● For the humanity :) ● See https://cloudxlab.com/blog/creating-ai-based-cameraman/
- 176. The Setup
- 177. How does it work? ● Read image from the USB camera ● Using OPENCV / YOLO identify the object in the image ● Keep only the persons ● For all the persons ○ Pick the one which has the biggest bounding box ● Rotate the motors to bring ○ Centre of the bounding box to centre of the main image, ● Sleep for some time, go back to step 1
- 178. Beyond 2D Object Detection... Object Detection + Captioning = Dense Captioning
- 179. Generative Adversarial Network (GANs) Image Generator Detector Real Fake By Ian J. Goodfellow, Yoshua Bengio and others in 2014. Yann LeCun called adversarial training “the most interesting idea in the last 10 years in ML.”
- 180. Generative Adversarial Network (GANs)
- 182. Face Embedding
- 184. Example Face Embedding Facenet Facenet Facenet Facenet [0.3, -0.1, 0.3, …… 128 numbers] [0.2, 0.1, 0.8, …… 128 numbers] [0.1, 0.2, 0.6, …… 128 numbers] [0.8, 0.9, 0.3, …… 128 numbers] Facenet [0.2, -0.1, 0.3, …… 128 numbers]
- 185. Example Face Embedding Facenet Facenet Facenet Facenet [0.3, -0.1, 0.3, …… 128 numbers] [0.2, 0.1, 0.8, …… 128 numbers] [0.1, 0.2, 0.6, …… 128 numbers] [0.8, 0.9, 0.3, …… 128 numbers] Facenet [0.2, -0.1, 0.3, …… 128 numbers]
- 188. DejaView.AI - It is a plug and play solution to recognize and recall your users. Few of the use cases are: Giving loyalty points to your users, letting your employees enter the premises based on the face recognition. Application of Computer Vision
- 189. Upskill Yourself - Get Certification From E&ICT Academy, IIT Roorkee ● Big Data Engineering with Hadoop and Spark ● Self-paced ● 60+ hours of learning ● Starts from $59 ● Machine Learning Specialization - Includes Python, Machine Learning and Deep Learning ● Self-paced ● 100+ hours of learning ● Starts from $99 ● Python Foundations for Machine Learning ● Self-paced ● 40+ hours of learning ● Starts from $99
- 190. Upskill Yourself ● AI for Managers ● For Technical product managers, project managers, business heads, senior managers and team leads ● Self-paced ● 60+ hours of learning ● Starts from $99