### What is the best and easiest software program for machine learning?

I am new for the AI, deep learning and machine learning stuff. I want to learn more about machine learning as fast and efficient as possible. What should I learn from these options: Pytorch, Keras or TensorFlow. P.S.: I don’t use python or any other programming language, but currently I’m learning Matlab.

### What is the most suitable AI technique to use?

So I am making a firetruck using arduino uno with flame sensors and ultrasonic sensors to detect how to move and where to go. As this is a project for my university, I am asked to implement AI in it for path planning. I am not sure whether to use something like A* technique or…

### How can policy gradient fulfill the required action range?

As we often use the gaussian policy for continuous action space, but how can we make it proper for the range. In spiningup’s implementation, I found they just simply used, def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activation, action_space): act_dim = a.shape.as_list()[-1] mu = mlp(x, list(hidden_sizes)+[act_dim], activation, output_activation) log_std = tf.get_variable(name=’log_std’, initializer=-0.5*np.ones(act_dim, dtype=np.float32)) std = tf.exp(log_std) pi…

### Discussion – Does AGI require a radical new idea?

I read an interesting essay about how far we are from AGI. There were quite a few solid points that made me re-visit the foundation of AI today. A few interesting concepts arose: imagine that you require a program with a more ambitious functionality: to address some outstanding problem in theoretical physics — say the…

### Why can’t LSTMs keep track of the “important parts” of a sequence?

I keep reading about how LSTMs can’t remember the “important parts” of a sequence which is why attention based mechanisms are required. I was trying to use LSTMs to find people name format. For example, “Millie Bobby Brown” can be seen as first_name middle_name last_name format, which I’ll denote as 0, but then there’s “Brown,…

### Training and inference for highly-context-sensitive information

What is the best way to train / do inference when the context matters highly as to what the inferred result should be? For example in the image below all people are standing upright, but because of the perspective of the camera, their location highly affects their skeletal pose. If the 2D inferred skeleton of…

### How can I write out the Real-TIme Recurrent Learning Gradient equations for a network?

This question is about Real-Time Recurrent Learning Gradient on a Recurrent neural network . How can I write out the RTRL equations for a network ? Before present an example give let’s introduce some notation : Notation So the network for which we want to write the RTRL equations is the following : Network A…

### Artificial Neurons affecting others at the same level

Isn’t it the case the the artificial neurons in layer X are only affected by those in layer X-1 (providing inputs), not other neurons in layer X? This is motivate by another recent question.

### How to determine mathematical membership functions and graphs?

How can we determine mathematical membership functions and graphs ? eg Fuzzy sets A, B and C defined on real numbers by the membership functions: $\mu_A(x)=\frac{1}{x+1}, \mu_B(x)=\frac{1}{x^2+10}, \mu_C(x)=\frac{1}{10^x}$ Determine mathematical membership functions and graphs of each of the following ? A $\cup$ B B $\cap$ C A $\cup$ B $\cup$ C A $\cap$ B $\cap$…