rehman04/deep_learning_for_computer_vision

Deep_Learning_For_Computer_Vision

---

There are 4 metrics in classification problem, which is super vised learning.

1. Accuracy
2. prescision
3. recall
4. f1score
5. confusion matrix.

---

Deep Learning:

Perceptron Model:

Inputs multiply by random weights, added a bias to avoid zero multiplication result, then activation function and then the output.

---

Activation Functions:

1. Simple activation has output 0 for -ve and 1 for +ve.
2. sigmoid output between 0 and 1
3. tanh(x) output between -1 and 1
4. Relu return max(0,x)

---

Cost Function: Quadratic Cost:

c = E(y-a)^2 / n it slow down in our learning speed

---

Cross Entropy:

This is for faster learning. The faster the learning rate as the difference between true value and prediction.

---

Gradient Descent and Back Propagation:

Gradient descent use to minimize the value of cost function. Back propagation calculate error contribution at each neuron after batch of data is processed.Its a methametical chain rule.It requires a known desired output of each input value.

---

YOLO V3 is trained model on COCO dataset of Microsoft, it has 80 different Classes YOLO

Audience:

• Beginners
• Intermediate
• Professionals