Machine Learning MASTER, Zero To Mastery
WHO CAN ACCESS THIS COURSE :-
- Computer Science Students
- Computer Science Graduated
- Computer Science Master Student
- Who wanna know Machine Learning
WHAT ARE YOUR REQUIREMENTS FOR THIS COURSE ?
- Basci knowledge of computing or programming may be.
WHAT YOU ARE GOING TO LEARN FROM THIS COURSE ?
- Machine Learning
- Deep Learning
- Artifical Intelligence
To being Machine Learning Mystery
I am certain various you have caught wind of AI. You twelve may even realize what it is. Furthermore, a few you may have worked with AI calculations as well.
You see where this is going? Not many individuals know about the innovation that will be significant a long time from now. Siri is AI. Amazon’s Alexa is AI. Promotion and shopping thing recommender frameworks are AI.
We should attempt to comprehend AI with a basic similarity of a long term old kid. For no particular reason, how about we call him Kylo Ren
How about we expect Kylo Ren saw an elephant. What will his mind let him know ?(Remember he has least reasoning limit, regardless of whether he is the replacement to Vader). His cerebrum will reveal to him that he saw a major moving animal which was dark in shading. He sees a feline next, and his cerebrum reveals to him that it is a little moving animal which is brilliant in shading. At last, he sees a light saber straightaway and his mind discloses to him that it is a non-living article which he can play with!
His mind now realizes that saber is not the same as the elephant and the feline, on the grounds that the saber is something to play with and doesn’t proceed onward its own. His cerebrum can make sense of this much regardless of whether Kylo doesn’t have the foggiest idea what versatile methods. This basic wonder is called Clustering .
AI is only the numerical adaptation of this cycle.
Many individuals who study insights understood that they can make a few conditions work similarly as mind works.
Cerebrum can group comparable items, mind can gain from missteps and cerebrum can figure out how to recognize things.
The entirety of this can be spoken to with insights, and the PC based reenactment of this cycle is called Machine Learning. For what reason do we need the PC based recreation? since PCs can do substantial math quicker than human cerebrums.
I couldn’t imagine anything better than to go into the numerical/factual piece of AI yet you don’t wanna bounce into that without clearing a few ideas first.
How about we return to Kylo Ren. Suppose Kylo gets the saber and starts playing with it. He inadvertently hits a stormtrooper and the stormtrooper gets harmed. He doesn’t comprehend what’s happening and keeps playing. Next he hits a feline and the feline gets harmed. This time Kylo is certain he has accomplished something terrible, and attempts to be fairly cautious. However, given his awful saber aptitudes, he hits the elephant and is certain beyond a shadow of a doubt that he is in a difficult situation.
He turns out to be incredibly cautious from that point, and just hits his father deliberately as we found in Force Awakens!!
- 6 sections • 79 lectures • 84h 36m total length
1 lecture • 11minML Master Lectures
- Let’s START!Preview11:09
18 lectures • 23hr 32minIntroduction to ML
- 01 The Learning ProblemPreview01:21:34
- 02 Is Learning Feasible01:16:54
- 03 The Linear Model I01:19:43
- 04 Error and Noise01:18:29
- 05 Training versus Testing01:17:05
- 06 Theory of Generalization01:18:14
- 07 The VC Dimension01:13:38
- 08 Bias-Variance Tradeoff01:16:58
- 09 The Linear Model II01:27:19
- 10 Neural Networks01:25:23
- 11 Overfitting01:19:56
- 12 Regularization01:15:21
- 13 Validation01:26:19
- 14 Support Vector Machines01:14:24
- 15 Kernel Methods01:18:31
- 16 Radial Basis Functions01:22:15
- 17 Three Learning Principles01:16:27
- 18 Epilogue01:03:27
20 lectures • 21hr 56minMachine Learning Master
- 01 Machine learning – introduction54:39
- 02 Machine learning – linear prediction01:03:06
- 03 Machine learning – Maximum likelihood and linear regression01:14:00
- 04 Machine learning – Regularization and regression01:01:14
- 05 Machine learning – regularization, cross-validation and data size58:41
- 06 Machine learning – Bayesian learning01:17:04
- 07 Machine learning – Bayesian learning part 221:09
- 08 Machine learning – Introduction to Gaussian processes01:18:54
- 09 Machine learning – Gaussian processes01:17:27
- 10 Machine learning – Bayesian optimization and multi-armed bandits01:20:29
- 11 Machine learning – Decision trees01:06:05
- 12 Machine learning – Random forests01:16:54
- 13 Machine learning – Random forests applications51:35
- 14 Machine learning – Unconstrained optimization01:16:18
- 15 Machine learning – Logistic regression01:13:30
- 16 Machine learning – Neural networks01:04:27
- 17 Machine learning – Deep learning I01:13:13
- 18 Machine learning – Deep learning II, the Google autoencoders and dropout01:12:02
- 19 Machine learning – Importance sampling and MCMC I01:16:17
- 20 Machine learning – Markov chain Monte Carlo (MCMC) II39:16
17 lectures • 22hr 59minApplied ML Master, Deep Learning
- Introduction to Machine Learning00:01
- Neural Networks I01:28:29
- Neural Networks II01:34:05
- Advanced Deep Vision01:33:54
- RAMP (Practical session)01:18:45
- Generative Models I01:29:36
- Optimization I01:09:46
- Optimization II01:24:15
- Recurrent Neural Networks (RNNs)01:30:39
- Language Understanding01:26:03
- Multimodal Learning01:19:43
- Computational Neuroscience01:34:52
- Bayesian Neural Nets01:31:40
- Deep Learning and Music01:28:58
11 lectures • 14hr 46minApplied ML Master, Reinforcement Learning
- Introduction to RL and TD01:29:24
- Policy Search01:29:34
- Batch RL and ADP01:31:51
- Off-Policy Learning01:22:11
- Bandits and Explore-Exploit in RL01:20:53
- Temporal Abstraction01:31:48
- Multi-task and Transfer in RL01:26:17
- Deep RL01:26:23
- Imitation Learning01:05:05
- Safety in RL01:00:38
- Multi-agent RL01:01:37
12 lectures • 1hr 13minINTEL Machine Learning TOOLKIT
- Week1 Introduction to Machine Learning and Toolkit08:30
- Week2 Introduction to Supervised Learning and K Nearest Neighbors05:55
- Week3 Train Test Splits Validation Linear Regression06:20
- Week4 Regularization and Gradient Descent06:00
- Week5 Logistic Regression_Classification Error Metrics_Final04:20
- Week6 Naive Bayes05:40
- Week7 SVM and Kernels06:50
- Week8 Decision Trees06:40
- Week9 Bagging04:10
- Week10 Boosting and Stacking05:35
- Week11 Intro to Unsupervised Learning08:30
- Week12 Dimensionality Reduction04:15